Axelera AI
Edge AI inference hardware and software
Advanced Packaging & Power Delivery Senior Engineer
More locations: Remote in Germany | Paris, France | Bristol, UK | Remote in Ireland | Milan, Metropolitan City of Milan, Italy | Remote in Spain | Remote in Italy | Florence, Metropolitan City of Florence, Italy | Remote in France
Fully remote from a European country where you already reside; relocation is available to Italy or the Netherlands. Priority is given to candidates based in Belgium or Italy.
About the job
- A Bachelor’s or Master’s degree in Electrical Engineering, Microelectronics, or a related field; a PhD is a plus.
- At least 7 years of experience in power delivery and/or advanced packaging design in a semiconductor or deep-tech environment.
- Demonstrated expertise in on-die power grid design and package/printed circuit board power delivery network analysis.
- Hands-on experience with 2.5D and/or 3D integrated-circuit packaging technologies, multi-chiplet integration, and interposer/substrate co-design.
- Proficiency with industry-standard electronic design automation tools for power integrity, power delivery network simulation, and package design.
- Ability to work cross-functionally and communicate complex technical trade-offs to diverse stakeholder groups.
- Strong written and spoken English communication skills.
- Own power-delivery design end to end, from on-die power grids to package and printed circuit board power delivery network design and analysis.
- Lead advanced packaging architecture decisions for 2.5D/3D stacking, multi-chiplet integration, and interposer/substrate co-design.
- Perform signal-integrity/power-integrity verification and sign-off across the full stack, ensuring power-integrity and signal-integrity targets are met.
- Collaborate with the AI Integrated Systems and Silicon Engineering teams to align power-delivery and packaging solutions with product and silicon requirements.
- Support thermal and integration reviews for current and future products.
- Develop and maintain power-delivery methodology, flows, and design guidelines within the Custom Design toolchain.
- Identify and mitigate single-point-of-failure risks in signal-integrity/power-integrity workstreams; mentor and grow the team’s packaging expertise.
- Engage with external partners, substrate/interposer vendors, and outsourced semiconductor assembly and test houses to co-develop advanced packaging solutions.
- Experience with signal-integrity/power-integrity verification and sign-off methodologies.
- Familiarity with thermal modeling and co-simulation for integrated packages.
- Exposure to AI accelerator or custom application-specific integrated circuit design flows.
- Experience collaborating with outsourced semiconductor assembly and test partners, substrate vendors, or research institutes such as imec.
- Knowledge of advanced-node custom and analog design practices.
About the company
Axelera AI provides hardware and software to run AI tasks on edge devices, using its Metis AI Processing Units (AIPUs) designed for efficient, high‑performance inference in power‑limited environments. These chips use Digital In‑Memory Computing (D‑IMC), performing calculations where data is stored to reduce data movement and speed up processing, with the Voyager SDK helping developers integrate and deploy AI applications. It differentiates itself with a Europe‑origin platform focused on technological sovereignty, prioritizing edge inference over cloud GPUs and offering a complete hardware‑software ecosystem for industries like manufacturing, retail, robotics, healthcare, and security. Its goal is to mass‑produce a European‑developed AI acceleration platform that makes AI at the edge more accessible and affordable.
Company Size
201-500
Company Stage
Series C
Total Funding
$454.7M
Headquarters
Eindhoven, Netherlands
Founded
2021
Get referred to Axelera AI
See people who can refer or advise you
Simplify's Take
What believers are saying
- February 24, 2026 funding raised over $250 million from Innovation Industries and BlackRock.
- Europa targets 629 TOPS and generative AI for robotics, automotive, and edge servers.
- ASRock Industrial and Intozi Tech partnerships expand deployment into industrial and government markets.
What critics are saying
- Europa samples slipped to Q2 2026 after a planned first-half launch.
- Nvidia Jetson and Thor threaten Europa's pricing and performance claims.
- Failure to convert 500 customers into durable production revenue risks a financing cliff.
What makes Axelera AI unique
- Metis and Europa use digital in-memory compute for low-power edge inference.
- Axelera shipped to its 500th customer by February 2026.
- Partner Accelerator Network quadrupled by September 2026, adding 60-plus partners.
Help us improve and share your feedback! Did you find this helpful?
Benefits
Remote Work Options
Hybrid Work Options
Company Equity
Growth & Insights and Company News
6 month growth
↑ 1%1 year growth
↑ 0%2 year growth
↑ 1%Ukrainian DoD Solution and Estonian Defsecintel will develop an AI system to intercept drones. 09 September, 2026, 16:58 Mykhailo Tarchynets DoD Solution and Defsecintel have signed a memorandum on strategic cooperation. The company told AIN about this. As part of the cooperation, the companies plan to combine the EIRSHIELD system with the AURA AI autonomy platform and test joint solutions in Ukraine, Estonia and other European countries. More about the cooperation between DoD Solution and Defsecintel. Defsecintel will provide its EIRSHIELD system, which delivers multi-layer threat detection and AI-based command and control. In turn, DoD Solution will integrate the AURA SBC onboard computer and the AURA AI platform. They will be responsible for visual navigation of drones, terminal guidance and autonomous mission execution. According to DoD Solution CEO Roman Hapachyla, Ukraine's experience demonstrates the need for a multi-layered approach to countering aerial attacks. That's why the new solutions are aimed not only at traditional military scenarios but also at protecting state borders and public safety. The developers plan to conduct joint tests of their systems in Ukraine, Estonia and other European countries. More about DoD Solution. DoD Solution - an Estonian-Ukrainian Defense Tech startup - was founded in 2023 by Lviv entrepreneurs Ivan Oleksiy and Nazar Kravchuk. The company creates embedded artificial intelligence and onboard computing platforms for unmanned systems that operate in challenging conditions. The startup also develops hardware and software that enable drones and robotic systems to navigate, perceive and act when GPS is unavailable and electronic warfare is present. More about Defsecintel. Defsecintel - an Estonian Defense Tech company - develops counter-drone systems, automated surveillance and unmanned solutions. Its systems combine sensors, command-and-control with AI support, and various counter-drone measures. Recall that in early August 2026 DoD Solution and Dutch Axelera AI announced a strategic partnership in the field of defense technologies. The companies plan to develop AI-enabled onboard computing solutions to be used in autonomous defense systems.
Callosum raises $100M to cut AI costs by routing workloads to specialized chips. 20 August 2026 Key Takeaways * Callosum raises $100 million led by Atomico, one of the largest early-stage rounds in UK history. * The startup routes AI tasks to cheap, specialized chips instead of defaulting to expensive Nvidia GPUs. * Founded by Cambridge neuroscientists, the platform assigns each workload to the most efficient model and chip. The human brain doesn't use one giant processor for everything. It uses small circuits built for specific jobs. AI companies do the opposite, and it's killing their margins. To change that, Callosum raises $100M to build software that routes AI tasks to the cheapest chip that can do the work. The round was led by Atomico, with participation from Plural and DCVC. It also marks the first investment from the UK's new Sovereign AI Fund. At £73.5M, it ranks among the largest seed rounds in UK history. The money comes at a critical time. As AI moves from training massive models to deploying them at scale, companies are discovering that running those models is where the real money burns. The problem Callosum solves. Most companies today run every AI task on expensive, general-purpose Nvidia GPUs. It doesn't matter if the job needs massive compute or just basic processing; it all gets the same premium chip. That brute-force approach is draining budgets fast. For many AI-native companies, inference takes up over 50% of revenue. Training gets the headlines, but inference is what determines if a business is profitable. Callosum routes compute like the human brain. Callosum's answer is to stop treating all compute the same. Founded by Cambridge neuroscientists Danyal Akarca and Jascha Achterberg, the company took inspiration from biology. The human brain doesn't use one giant processor for everything. It uses small, specialized neural circuits tailored for specific actions. Callosum built software that does the same for AI. It acts as a smart routing layer between applications and hardware. It breaks down complex AI tasks and automatically assigns each piece to the cheapest, most efficient model and chip available. Instead of defaulting to Nvidia, Callosum partners with specialized chipmakers including Axelera, Cerebras, and Rebellions. A simple task gets a simple chip. A complex task gets the heavy hardware. 70% savings and 4X speed. The results are already showing up in early deployments. In partnership with chipmaker Cerebras on financial agentic workloads, Callosum reports 70 percent reductions in cost. By matching tasks to specialized silicon instead of general GPUs, it's also delivering 4 times speed gains. The pitch to investors is simple: the next phase of AI isn't about buying more chips. It's about using the hardware you already have as efficiently as possible. "Running generative AI models is wildly expensive," the company notes. Callosum wants to change how software talks to physical microchips so companies stop overpaying. The AI market is shifting. The race to train foundational models is slowing, but the race to deploy them cheaply is accelerating. That makes workload orchestration the next major hardware battleground. With backing from Atomico and the UK government, Callosum is positioning itself at the centre of it. The future of AI compute, the founders argue, isn't running every task on the biggest GPU available. It's picking the right tool for the job, just like the brain does. I'm a crypto writer with 4+ years of experience passionate about turning big, technical ideas into content anyone can understand. From blockchain to stablecoins to everything in between, I enjoy helping readers stay informed in a space that never stops moving. Disclaimer VentureBurn is a media platform covering the latest in cryptocurrency, artificial intelligence, venture capital, and the startup ecosystem. Opinions expressed on VentureBurn are for informational purposes only and do not constitute investment advice. Before making any high-risk investments in digital assets or emerging technologies, readers should conduct their own due diligence. All transactions and financial decisions are made at your own risk, and any losses incurred are solely your responsibility. VentureBurn does not endorse or recommend the buying or selling of any digital assets and is not a licensed investment advisor. Please note that VentureBurn may participate in affiliate marketing programs.
Intozi Tech partners with Axelera AI to power next-generation Vision AI. Partnership brings high-performance, energy-efficient AI inference to government, industrial, and enterprise deployments globally. GURUGRAM, INDIA, August 18, 2026 / EINPresswire.com / - Intozi Tech Pvt. Ltd., a deep-tech Vision AI company and developer of the Ikshana AI video analytics platform, today announced a strategic partnership with Axelera AI, a Netherlands-based AI acceleration company, to deploy Vision AI solutions at the edge using Axelera's Metis AI Processing Unit (AIPU). Under this partnership, Intozi's Ikshana platform will run on Axelera's devices, enabling governments, industries, and enterprises to deploy AI-powered video analytics at scale across critical infrastructure, public safety, manufacturing, oil & gas, airports, and smart city environments, without dependence on cloud infrastructure or high-cost GPU hardware. Why This Partnership Matters Organizations deploying large-scale video analytics face a common challenge: real-time AI inference across hundreds of camera streams, in environments where cloud connectivity is limited and data sovereignty is non-negotiable. Intozi's Ikshana platform currently powers 300+ AI use cases across 500+ customers globally. As these deployments grow in scale and complexity, the need for purpose-built, high-efficiency edge compute has become mission-critical. Internal benchmarking of Ikshana on Axelera's Metis AIPU has surpassed Intozi's own prior performance benchmarks, delivering 2.7x higher throughput per stream. This enables Intozi to deploy more cameras per device, reduce total cost of ownership, and extend AI-powered analytics to locations where inference speed is critical and bandwidth is constrained. "At Intozi, we've always believed that the real value of Vision AI is unlocked at the edge, where decisions need to happen in real time, at scale. Axelera's Metis AIPU gives us the hardware foundation to deliver exactly that. This partnership marks a significant step in our mission to make intelligent video analytics accessible, efficient, and scalable for every deployment, everywhere." - Virender Josan, Founder & MD, Intozi Tech Pvt. Ltd. "Our mission is to bring industry-leading AI performance without the usual tradeoffs in cost, power, or complexity. Intozi has built one of the most capable Vision AI platforms in the market, with proven deployments across demanding government agencies, industrial facilities, and enterprise environments. We're excited to partner with them to bring the performance of the Metis AIPU to their customers across the globe. Together, we are demonstrating that edge AI no longer needs to be a compromise between performance and cost." - Stephanie Muh, Head of Americas' Partnerships, Axelera AI About Intozi Tech Pvt. Ltd. Intozi Tech is a deep-tech Vision AI company headquartered in Gurugram, India. With 7+ years in the market and an established 500+ customer base across government, industrial, and enterprise sectors, its flagship platform, Ikshana, delivers 300+ ready-to-deploy AI-powered video analytics use cases with no-code customization for new use case development. For more information, visit https://intozi.io/ Legal Disclaimer: EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.
ASRock, Axelera AI advance Edge AI deployment. July 21, 2026 ASRock Industrial has partnered with Axelera AI to provide efficient, high-performance AI inference solutions tailored for edge computing applications. By integrating Axelera's Metis AI Processing Unit (AIPU) cards into ASRock Industrial's edge AI platforms, the collaboration delivers a compact and scalable solution capable of adding up to 214 TOPS of AI inference through M.2 or PCIe accelerator cards. Powered by the Metis AIPU, the platform offers strong AI performance with lower power consumption and reduced total cost of ownership compared to traditional GPU-based systems. The solution is designed for edge AI use cases such as large language models (LLMs), machine vision, robotics, smart retail, and smart city deployments, enabling organizations to process AI workloads closer to the data source while reducing infrastructure, energy, and space requirements. Validated Edge AI platforms accelerate deployment. These validated configurations provide customers with a scalable path to deploying advanced AI capabilities on compact edge systems. On ASRock Industrial's expandable Edge AIoT platforms, including the iEPF-11000S, iEPF-10000S, iEPF-9500S, iEPF-9040S, and iEPF-9040VS series, the Axelera Metis PCIe card enables scalable, industrial-grade AI processing for demanding edge applications. For compact edge systems such as the AI BOX-A395, NUC BOX-358H, NUC BOX-255H, and NUC BOX-155H, the Axelera Metis M.2 card delivers high-performance AI inference in a compact, power-efficient form factor. Supporting multiple AI workloads running in parallel, these solutions enable real-time analysis for machine vision, robotics, retail and hospitality, warehouse automation, smart surveillance, and intelligent transportation. "Organizations are looking for practical ways to scale AI beyond proof-of-concept projects," said James Lee, Chairman of ASRock Industrial. "By combining Axelera AI Metis AIPU cards with ASRock Industrial's edge computing platforms, we provide customers with greater flexibility to deploy AI where it delivers the most value. This collaboration expands the range of AI solutions available for industrial and enterprise environments while simplifying the path from development to deployment." "Advanced AI shouldn't require oversized systems or power budgets most environments can't support," said Fabrizio Del Maffeo, CEO and Co-Founder of Axelera AI. "Our collaboration with ASRock Industrial pairs Axelera's high-performance AIPUs with proven industrial computing platforms, giving customers a practical way to run demanding AI workloads within the constraints their systems must work within." As demand for edge AI continues to grow, ASRock Industrial and Axelera AI are committed to delivering solutions that make advanced AI more accessible across edge environments. By combining compact, high-performance AI acceleration with proven edge computing platforms, the collaboration enables organizations to deploy AI workloads more efficiently and unlock new opportunities for intelligent automation, machine vision, and real-time decision-making at the edge. To simplify platform selection and accelerate AI deployment, ASRock Industrial continues expanding its AI Pathfinder tool with validated hardware recommendations, integrating accelerator cards, GPUs, and optimized platform configurations tailored for diverse AI workloads and deployment scenarios. Through AI Pathfinder, customers can more efficiently identify recommended Edge AI systems and accelerate deployment decisions with confidence.
Axelera AI, a Netherlands-based startup serving over 500 customers, has raised €250 million in a Series C round led by Innovation Industries to scale its edge-first AI architecture. The company develops purpose-built silicon chips for AI inference at the edge, eliminating the need for cloud computing in manufacturing and industrial environments. CEO Fabrizio Del Maffeo explained that edge-first architecture integrates memory directly with compute, enabling real-time AI decision-making within tight power budgets. The approach allows manufacturers to run AI locally, reducing costs, maintaining data sovereignty and eliminating latency issues critical for industrial robots and equipment. The funding will support scaling its Metis product line, launching Europa in summer 2026 and advancing its Titania chiplet architecture. Six new partners recently joined Axelera's Partner Accelerator Network to deploy solutions across various industries.