Member of Technical Staff - Research, Inference

Highlights

• Own end-to-end inference research bets from idea to production impact.
• Shape serving platform used for training, deployment, and observability.
• Partner directly with customers to deploy and tune models in production.

What they offer

• Equity

Ideal candidate

Independent, research-driven builder who loves taking inference ideas from prototype to production. Motivated by real-world cost and latency wins and collaborating openly with engineers and customers.

Requirements

• Research-leaning or systems background in LLM inference, with work you can point to
• Fluency in the LLM serving stack, from kernels and quantization up to schedulers and autoscaling
• Record of shipping research or systems that other people build on, whether in a lab or in industry
• Drive to independently take a research bet from idea to result, working in the open with the rest of the team
• Ability to work in-person in NYC or San Francisco office