Full Stack Engineer

About The Role

RadixArk is building the infrastructure layer for frontier AI systems — unified inference, training, and evaluation stacks powering next-generation LLM applications at scale. Our platform integrates high-performance model serving, RL pipelines, and large-scale distributed systems across GPUs, TPUs, and emerging accelerators. We work at the intersection of systems engineering, AI research, and developer experience. We are looking for a world-class Full Stack Engineer who thrives in high-ambiguity environments and wants to build foundational tools for the next decade of AI.

Requirements

Technical Excellence

• 4+ years of professional full stack engineering experience
• Based in Palo Alto, CA (Hybrid) / Remote (U.S.)
• Deep experience in:
  • Frontend: React / Next.js / TypeScript
  • Backend: Python (FastAPI / Django) or Node.js
  • RESTful and/or gRPC API design
• Strong understanding of distributed systems concepts
• Experience building systems that handle real-time streaming or high-throughput workloads
• Strong database design skills (Postgres, Redis, etc.)
• Familiarity with containerized environments (Docker, Kubernetes)
• Strong software engineering fundamentals: testing, CI/CD, version control, design reviews

Bonus (High Impact)

• Experience building developer tools or infrastructure platforms
• Experience in ML infrastructure, model serving, or AI tooling
• Familiarity with observability stacks (Prometheus, Grafana, OpenTelemetry)
• Experience with WebSockets or streaming architectures
• Performance optimization at scale
• Experience building internal platforms used by engineers

Responsibilities

You will own end-to-end product surfaces across our developer platform:

• Design and implement high-performance web applications for AI infrastructure tooling
• Build scalable backend systems that interact with distributed inference and training services
• Architect APIs and service layers that serve enterprise and research customers
• Develop observability dashboards, experiment tracking UIs, and performance analytics tools
• Optimize real-time streaming interfaces for model inference workflows
• Work closely with ML engineers and infra teams to expose complex systems through intuitive product surfaces
• Lead architectural decisions for frontend-backend communication, state management, and performance tuning
• Ship production-grade features in fast iteration cycles

You will not just “write UI.” You will build the control plane for frontier AI systems.

Your work will directly power:

• Large-scale LLM inference systems
• Reinforcement learning training platforms
• Evaluation and experimentation frameworks
• Developer-facing AI infrastructure products

This is not CRUD dashboard engineering. This is building the operating system for AI builders.

About RadixArk

RadixArk is an infrastructure-first company built by engineers who've shipped production AI systems, created SGLang (20K+ GitHub stars, the fastest open LLM serving engine), and developed Miles (our large-scale RL framework). We're on a mission to democratize frontier-level AI infrastructure by building world-class open systems for inference and training. Our team has optimized kernels serving billions of tokens daily, designed distributed training systems coordinating 10,000+ GPUs, and contributed to infrastructure that powers leading AI companies and research labs. We're backed by well-known infrastructure investors and partner with NVIDIA, Google, AWS, and frontier AI labs. Join us in building infrastructure that gives real leverage back to the AI community.