About the Role
The role
You'll own the cost and performance of our inference stack. Your work will determine how efficiently we serve models as workloads, traffic, and hardware change.
You'll work closely with the engineers operating the serving fleet while owning the core performance levers: caching, batching, quantization, decoding, and kernel-level optimization. Success means improving throughput and latency without compromising reliability or model quality.
Responsibilities
- Improve throughput, cost, and tail latency through KV-cache management, continuous batching, speculative decoding, and quantization.
- Optimize long-context prefill and decode workloads based on real production traffic.
- Tune routing between our infrastructure and external providers based on cost, capacity, and performance.
- Work within serving engines such as vLLM, SGLang, and TensorRT-LLM, going below the framework when needed.
- Build profiling and measurement systems that show where time, memory, and compute are being spent.
Qualifications
- 5+ years in ML systems, inference infrastructure, or performance engineering, with measurable improvements in cost or latency.
- Deep understanding of model serving, including prefill and decode, memory bandwidth, batching, and concurrency.
- Production experience with serving engines such as vLLM, SGLang, or TensorRT-LLM.
- Strong Python skills and proficiency in C++, Rust, or another systems language.
- Experience with GPU performance, including CUDA, NCCL, mixed precision, memory layout, kernels, or quantization.
Above all, we're looking for great teammates who make work feel lighter and aren't afraid to go out on a limb with bold ideas. You don't need to be perfect, but you do need to be adaptable. We encourage you to apply, even if you don't check every box.
About Us
Most AI is frozen in place - it doesn't adapt to the world. We think that's backwards. Our mandate is to build efficient intelligence that evolves in real-time. Our vision is AI systems that are flexible, personalized, and accessible to everyone. We believe efficiency is what makes this possible - it's how we expand access and ensure innovation benefits the many, not the few. We believe in talent density: bringing together the best and most driven individuals to push the boundaries of continual adaptation. We're looking for builders and creative thinkers ready to shape the next era of intelligence.
Benefits
- Flexible work: In-person collaboration in the Bay Area, a distributed global-first team, and team offsites.
- Adaption Passport: Annual travel stipend to explore a country you've never visited.
- Lunch Stipend: Weekly meal allowance for take-out or grocery delivery.
- Well-Being: Comprehensive medical benefits and generous paid time off.
Requirements
ML systems experience
5+ years in ML systems, inference infrastructure, or performance engineering.
Model serving knowledge
Deep understanding of model serving, including prefill and decode.
Serving engines experience
Production experience with serving engines such as vLLM, SGLang, or TensorRT-LLM.
Programming skills
Strong Python skills and proficiency in C++, Rust, or another systems language.
GPU performance experience
Experience with GPU performance, including CUDA and quantization.
Nice to Have
Ability to be adaptable and embrace bold ideas.
Great teammate who makes work feel lighter.
Benefits
Flexible work
In-person collaboration in the Bay Area and a distributed global-first team.
Adaption Passport
Annual travel stipend to explore a country you've never visited.
Lunch Stipend
Weekly meal allowance for take-out or grocery delivery.
Well-Being
Comprehensive medical benefits and generous paid time off.