R

RadixArk

Open-source AI infrastructure for large-scale inference

Member of Technical Staff - Product

Full-Stack EngineeringConfirmed live in the last 24 hours
Full-timeIn-person

About the Job

Requirements

  • A bachelor's degree in Computer Science, Computer Engineering, or a relevant technical field, or equivalent practical experience.
  • At least 5 years of software engineering experience building production systems, or at least 3 years with a PhD in a relevant field.
  • Strong programming skills in at least one of Python, TypeScript/JavaScript, Go, C++, or Rust.
  • Demonstrated experience shipping developer-facing or product-facing software end-to-end, including APIs, SDKs, web applications, or developer tools.
  • Experience using data and analysis to explain technical problems, prioritize work, and inform design decisions.
  • Experience collaborating and communicating effectively, with a track record of driving complex technical projects across teams.

Responsibilities

  • Collaborate with cross-functional teams in Product, Design, Research, Infrastructure, and Developer Relations to design and ship developer-facing products on the company's inference and training platforms.
  • Build and maintain customer-facing APIs, SDKs, command-line interfaces, dashboards, and playgrounds that expose the inference and serving infrastructure through intuitive, well-documented interfaces.
  • Implement custom user interfaces and developer experiences using modern frontend and backend technologies, with attention to performance, accessibility, and quality.
  • Architect efficient and scalable systems that bridge low-level infrastructure—including GPU scheduling, model serving, and distributed training—with high-level product surfaces.
  • Analyze and optimize code for quality, efficiency, and performance, and provide feedback to peers during code reviews.
  • Own components, features, or systems end-to-end, from initial design through rollout, monitoring, and iteration.
  • Set direction and goals for product engineering initiatives, lead major launches, and provide technical guidance and mentorship to peers and new team members.
  • Identify and resolve performance, reliability, and scalability issues across the product stack, and drive efforts to reduce technical debt.
  • Participate in design reviews and technical discussions, evaluating trade-offs between system complexity, developer experience, and time to ship.
  • Work with Product Managers to translate roadmap priorities into scoped technical deliverables, surface trade-offs, and resolve ambiguity early.
  • Engage directly with early adopters, design partners, and the open-source community to understand pain points and iterate on product experiences.
  • Contribute technical content, including documentation, code samples, blog posts, and demos, to help developers use the company's products.
  • Use data, telemetry, and user feedback to validate hypotheses, measure launch impact, and inform future work.

Desired Qualifications

  • Experience building products on AI/ML infrastructure, model-serving systems, or large-scale distributed systems.
  • Familiarity with LLM inference and training stacks such as SGLang, vLLM, TensorRT-LLM, PyTorch, Megatron, DeepSpeed, and Ray, and understanding of the trade-offs involved in serving and training large models.
  • Experience contributing to or maintaining open-source projects, especially in the AI/ML or infrastructure ecosystem.
  • Hands-on experience designing developer experiences such as public APIs, SDKs, command-line interfaces, or dashboards where developer ergonomics drive adoption.
  • Product sensibility and comfort making thoughtful user-experience and API design decisions rather than only executing specifications.
  • Experience improving quality through code reviews, testing, careful rollout, monitoring, and proactive iteration.
  • Demonstrated ability to integrate AI tools into engineering workflows to drive measurable efficiency gains or quality improvements.
  • Experience working in B2B, developer-facing, or infrastructure product environments.

About the Company

RadixArk

Open-source AI infrastructure for large-scale inference

RadixArk develops large-scale AI infrastructure for training and deploying models. Its core offering is the open-source SGLang engine that accelerates model inference, complemented by Miles, an open-source framework tailored for large-scale reinforcement learning and post-training tasks. The company provides managed infrastructure and production-grade tooling for model inference and post-training, with additional commercial products built on top of its open-source foundations. Revenue comes from managed hosting services and other paid offerings. Unlike many competitors, RadixArk pursues an open-core model to keep its core technology open and accessible to researchers, startups, and enterprises while monetizing via hosted services and premium tools. The goal is to democratize frontier AI infrastructure, reducing duplicated effort and enabling the AI community to train, deploy, and operate advanced models more efficiently and affordably.

Company size
51-200
Company stage
Seed
Total funding
$100M
Headquarters
Palo Alto, CA
Founded
2025

Recently Posted Jobs

Explore more opportunities at RadixArk

See more jobs