Member of Technical Staff, Inference Systems

We are looking for a Member of Technical Staff, Inference Systems with 2+ years of experience to help build a high-performance AI inference platform from the ground up. You are a systems engineer who lives and breathes inference internals – attention, KV cache, batching, scheduling – and you want to own the entire stack rather than work on a narrow slice. You'll join a small, fast-moving team building a new inference system in Rust, where every design decision is yours to shape. If you've spent time inside engines like vLLM, SGLang, or TensorRT-LLM and want to do the most impactful work of your career, this is the role.

What will you be doing?

• Build a new inference runtime from scratch in Rust – owning batching, scheduling, request routing, and the full serving stack.
• Design and implement KV cache management, prefix caching, and optimizations that directly reduce latency and cost per token.
• Scale serving across GPUs and nodes, tackling multi-GPU and multi-node challenges head-on.
• Profile, benchmark, and ship performance improvements across the entire inference pipeline.
• Collaborate closely with a small founding team to make core architectural decisions that define the platform.