Member of Technical Staff - Inference

Highlights

• Build multi-tenant LLM serving across cloud GPU fleets at scale.
• Embed optimized inference into RL training for frontier models.
• Shape open superintelligence stack for long-horizon AI tasks.

What they offer

• Significant equity incentives
• Flexible work arrangement - remote or San Francisco office
• Full visa sponsorship and relocation support
• Professional development budget
• Regular team off-sites and conference attendance

Ideal candidate

Systems-minded engineer excited by frontier AI infrastructure who thrives owning large-scale services end-to-end and wants to turn research breakthroughs into reliable, open platforms.

Requirements

• 3+ years building and running large-scale ML/LLM services with latency/availability SLOs
• Hands-on with vLLM, SGLang or TensorRT-LLM
• Familiarity with distributed and disaggregated serving infrastructure such as NVIDIA Dynamo
• Deep understanding of prefill vs decode, KV-cache, batching, sampling and parallelism strategies
• Comfortable debugging CUDA/NCCL, kernels, containers, networking and storage end-to-end
• Experience with Python, PyTorch, AWS/GCP, Kubernetes and GPU networking