CoreWeave
GPU-accelerated cloud computing platform
AI Engineer - Field Engineering
+ Discretionary bonus + Equity awards
More locations: New York, NY, USA | Sunnyvale, CA, USA
About the job
- At least 3 years of professional software engineering experience with strong proficiency in Go or Python.
- Experience taking an AI application from prototype to production use and supporting it afterward.
- Hands-on experience with agent patterns, including tool and function calling, multi-step orchestration, and handling incorrect model output.
- Experience building and evaluating retrieval systems, including measuring quality against a baseline using held-out data.
- Experience designing controls for automation that acts on production systems, such as approval steps, idempotency, and audit trails.
- Experience diagnosing failures in large language model applications and fixing the underlying cause rather than the symptom.
- Experience with observability for large language model applications, including tracing, cost, and latency.
- Working knowledge of Kubernetes and experience deploying services through continuous integration and continuous delivery.
- Experience integrating with third-party application programming interfaces, including authentication and secrets handling.
- Design and build AI agents that investigate and act on real customer issues.
- Build safeguards that ground model output in authoritative data, require human approval before consequential actions, and define conditions under which the system should stop.
- Build and evaluate retrieval over historical support data against how experienced engineers handled the same problems.
- Determine the optimal balance between AI and deterministic logic.
- Instrument AI systems for quality, cost, and adoption, then use the findings to decide what to build next.
- Deploy and operate services on Kubernetes, including supporting them when something breaks.
- Partner with support engineers and domain experts, including participating in live investigations to identify where automation helps and where it creates friction.
- Experience building conversational or chat-based interfaces for internal users.
- A background in infrastructure, site reliability engineering, or technical support, with comfort reading logs and metrics from a live system.
- Experience testing both deterministic and non-deterministic systems.
- Experience with fine-tuning or building training datasets from production data.
- Open-source contributions to AI tooling or agent frameworks.
About the company
CoreWeave provides cloud computing resources tailored for GPU-accelerated workloads. It offers high-performance, pay-as-you-go access to NVIDIA GPU hardware hosted on bare-metal servers managed by Kubernetes, enabling tasks such as Generative AI, machine learning, LLM inference, VFX rendering, and pixel streaming. Users run GPU-intensive workloads on a fully managed, serverless Kubernetes platform without needing to own or manage the underlying hardware. The company differentiates itself by specializing in GPU workloads, offering a wide range of NVIDIA GPUs, and reducing operational burden through its bare-metal, Kubernetes-based infrastructure. CoreWeave’s goal is to deliver scalable, cost-efficient, high-performance infrastructure for AI, HPC, and digital content creation workloads.
Company Size
1,001-5,000
Company Stage
IPO
Headquarters
Livingston, New Jersey
Founded
2017
Get referred to CoreWeave
See people who can refer or advise you
Simplify's Take
What believers are saying
- Q2 2026 revenue hit $2.6 billion, up 112%, with $104 billion backlog.
- August 20, 2026: Hudson River Trading chose CoreWeave for next-gen Rubin research.
- September 2026 storage upgrades cut latency 8x, improving inference economics for agents.
What critics are saying
- September 17, 2026: $3.5 billion convertible debt and 35 million-share ATM extend dilution.
- August 7, 2026: $2.6 billion DDTL charges SOFR plus 5.50%, crushing margins.
- Microsoft drove 67% of 2025 revenue; Denton delays and lawsuits threaten renewal trust.
What makes CoreWeave unique
- September 16, 2026: first multi-rack NVIDIA Vera Rubin NVL72 cloud cluster.
- CoreWeave embeds Mission Control, Racky, and Valvey to orchestrate racks end-to-end.
- September 10, 2026: Physical AI Field Engineering couples engineers with customer proprietary data.
Help us improve and share your feedback! Did you find this helpful?
Benefits
Health Insurance
Dental Insurance
Vision Insurance
Life Insurance
Disability Insurance
Health Savings Account/Flexible Spending Account
Tuition Reimbursement
Mental Health Support
Family Planning Benefits
Paid Parental Leave
Hybrid Work Options
401(k) Company Match
Unlimited Paid Time Off
Catered lunch each day in our office and data center locations
A casual work environment
Growth & Insights and Company News
6 month growth
↓ -1%1 year growth
↑ 0%2 year growth
↑ 0%CoreWeave launched a $3.0 billion convertible senior notes offering on 17 September 2026, with an option for an additional $500 million. The notes, due in 2033, are being sold to qualified institutional buyers. The company plans to use proceeds to fund capped call transactions aimed at limiting dilution from potential note conversions, with remaining funds allocated to general corporate purposes. CoreWeave simultaneously entered an Equity Distribution Agreement to sell up to 35 million shares of Class A common stock. The agreement includes collared forward sale structures designed to optimise pricing and provide hedging flexibility. Both initiatives support CoreWeave's broader strategy to expand funding options, manage equity dilution, and work towards achieving investment-grade credit status. The cloud infrastructure provider specialises in AI workloads and went public on Nasdaq in March 2025.
CoreWeave brings multi-rack Nvidia Vera Rubin NVL72 cluster online - to give agentic AI customers greater scale, faster iteration. Published: Sep 16 2026, 07:00 PM IST * FB * TW * Linkdin * Whatsapp * GNFollow Us CoreWeave added new storage capabilities designed to keep data closer to computing resources across regions and lower long-term storage costs. * CoreWeave's multi-rack deployment connects hundreds of Nvidia Rubin GPUs into one cluster. * Each Vera Rubin NVL72 rack combines 72 Rubin GPUs and 36 Vera CPUs. * CoreWeave added cross-region write acceleration and a new lower-cost Archive storage tier. CoreWeave Inc. (CRWV) stock is in focus on Wednesday after the company said it brought up a multi-rack Nvidia Vera Rubin NVL72 cluster on CoreWeave Cloud, connecting hundreds of Nvidia Rubin graphics processing units (GPUs) into a single system for agentic AI workloads. The multi-rack setup allows training and inference workloads to run across hundreds of Rubin GPUs, providing capacity for larger models, more demanding inference and reinforcement learning at scale, according to CoreWeave. Hundreds of Rubin GPUs connected as one cluster. A single Nvidia Vera Rubin NVL72 rack combines 72 Rubin GPUs with 36 Vera CPUs, alongside Nvidia networking and data-processing technology. CoreWeave said multiple racks are connected via Nvidia Spectrum-X Ethernet to operate as a single scale-out cluster. CoreWeave was the first AI cloud provider to validate and bring up a Vera Rubin NVL72, according to Chen Goldberg, Executive Vice President of Product and Engineering. "With multi-rack Vera Rubin, we are connecting hundreds of Rubin GPUs as a single scale-out cluster," Goldberg said, adding that the system gives customers building agentic AI greater scale and faster iteration. CoreWeave's infrastructure automates rack setup, firmware updates, validation, power and cooling. It also tests full racks before moving them into production. CoreWeave adds new storage features. Alongside the compute expansion, CoreWeave introduced cross-region write acceleration for its AI Object Storage platform. This allows AI workloads to write data in the region where they run, while CoreWeave copies it to another region in the background. This can reduce pauses for customers running training workloads across multiple regions, according to the company. The AI cloud-computing company also introduced an Archive tier, a lower-cost storage option for data customers want to retain longer. This tier has no retrieval fee, early-deletion fee, or fee for reading data from the Archive tier. Its Local Object Transport Accelerator, or LOTA, can also cache data closer to AI workloads, with CoreWeave saying it reduces read latency by 8x compared with reading from a traditional storage cluster. What retail investors think about CRWV hunt stock. Retail sentiment around CRWV stock continues to remain in 'bearish' territory on Stocktwits. So far this year, CoreWeave shares have risen around 2%. In comparison, ARK Innovation ETF (ARKK), which holds CRWV stock, has risen over 6% while the iShares AI Innovation and Tech Active ETF (BAI) has risen more than 25% during this period. For updates and corrections, email newsroom[at]stocktwits[dot]com.< Stay updated with all the latest Business News, including market trends, Share Market News, stock updates, taxation, IPOs, banking, finance, real estate, savings, and investments. Track daily Gold Price changes, updates on DA Hike, and the latest developments on the 8th Pay Commission. Get in-depth analysis, expert opinions, and real-time updates to make informed financial decisions. Download the Asianet News Official App from the Android Play Store and iPhone App Store to stay ahead in business. 0 Comments / 0 New
Cerebras Systems and CoreWeave represent distinct approaches to AI infrastructure, offering investors different risk-reward profiles for 2026. Cerebras builds wafer-scale processors for intensive computing workloads, whilst CoreWeave provides specialised cloud services for generative AI. Cerebras reported revenue of $510 million in fiscal 2025, up 75.7% year-on-year, and achieved profitability with net income of $237.8 million. However, free cash flow was negative at $392.8 million. CoreWeave showed more explosive growth, with revenue reaching $5.1 billion, up 167.9%. The company remains unprofitable, posting a net loss of $1.2 billion. CoreWeave faces concentration risk, with Microsoft accounting for roughly 67% of revenue, though agreements with Meta Platforms suggest diversification efforts. Both companies serve the rapidly expanding AI computing market but differ significantly in scale, profitability, and business model maturity.
CoreWeave closed a $2.6 billion delayed-draw term loan in August at SOFR plus 5.50%, whilst Nebius secured roughly $775 million in July at SOFR plus 2.50%. The three-percentage-point spread reflects different collateral structures rather than market sentiment alone. Nebius's facility is backed by deployed GPU infrastructure and cash flows from an investment-grade customer, covering over 100% of the underlying capital expenditure. CoreWeave's broader facility finances committed deployments across multiple customers and matures in September 2031, offering greater flexibility but raising the hurdle rate on each financed GPU. Hedge fund holdings rose for both companies in Q2 2026. CoreWeave's count increased to 71 from 63, whilst Nebius grew to 86 holders from 60. Lenders will finance AI capacity aggressively when contracts and customer credit support the loan, but charge substantially more when absorbing additional risk.
CoreWeave CEO Michael Intrator told investors at a recent tech conference that the company is "struggling to meet demand every day," signalling continued strong appetite for AI infrastructure. The statement comes as CoreWeave's stock has declined 24% over the past year, currently trading around $84 compared to its 52-week high of over $153. The AI infrastructure provider reported second-quarter sales of $2.6 billion, up 112% year-over-year. However, the company posted a $49 million operating loss, alongside $640 million in interest costs. Despite profitability concerns, CoreWeave's adjusted EBITDA reached $1.5 billion in Q2, double the $753 million reported a year earlier. The company provides customers access to Nvidia's high-end chips for AI applications.