Senior Machine Learning Engineer

We are working with an early stage Palo Alto company building high performance infrastructure for agentic AI systems.

The immediate focus is TPU and GPU inference serving with a longer term vision of infrastructure that supports self improving models and agents.

The Role

You will work directly with the founders to build production serving systems with a focus on latency throughput reliability cost and deployment speed.

The work may include distributed inference scheduling runtime optimization observability and infrastructure for large scale agent workloads.

Experience

Strong background in ML systems AI infrastructure or model serving

Experience with distributed inference training or low latency systems

TPU experience is highly valuable although strong GPU experience is also relevant

Useful technologies include Kubernetes Ray Slurm PyTorch JAX CUDA Triton vLLM SGLang TensorRT and Bazel

Package

Cash compensation can reach 500000 to 600000 dollars for exceptional candidates

Meaningful founding equity typically around 1 to 2 %