1-8 years of hands-on experience in ML infrastructure or applied LLM research engineering, preferably in a fast-growing AI startup or leading AI lab.
Strong proficiency in Python and PyTorch, with familiarity in C++/CUDA, Triton, or JAX.
Demonstrated success in optimizing LLM serving tools like vLLM, SGLang, or TensorRT-LLM.
Self-motivated with a strong sense of ownership over projects.
Willingness to work in person 5 days a week in the Bay Area.
Responsibilities
Measure and enhance the performance of specialized language models in production, focusing on response time and resource efficiency.
Develop testing setups and reinforcement learning environments based on real customer AI-agent interactions for continuous model improvement.
Collaborate closely with founders and business partners to integrate improved models into critical customer workflows with reliability targets.
Transform successful research experiments into reusable components for team and production use.
Manage tools for GPU allocation across model training and live serving operations.
Benefits
Opportunity to work directly with founders and influential business partners.
Engagement in cutting-edge AI projects with real-world impact.
Collaborative work environment focused on innovation and model improvement.
Access to advanced tools and technologies in ML infrastructure.
Full Job Description
Responsibilities
Measure and improve how fast and efficiently specialized language models run in real production use, including response time, throughput, GPU usage, memory caching, batching, and model compression (quantization).
Build testing setups, scoring tools, and reinforcement learning environments from real customer AI-agent activity, so that day-to-day usage feeds a steady cycle of model improvement.
Work directly with the founders and business partners to put improved models into important customer workflows that have strict reliability targets.
Turn successful research experiments into reusable building blocks that teammates, customer agents, and production systems can use.
Build and maintain the tools that manage GPU allocation across model training and live serving.
Requirements
1-8 years of hands-on experience in ML infrastructure, inference optimization, or applied LLM research engineering, at a fast-growing AI startup or a leading AI lab.
Strong skills in Python and PyTorch, plus at least some of C++/CUDA, Triton, or JAX.
Proven experience speeding up LLM serving tools such as vLLM, SGLang, or TensorRT-LLM.
Self-driven and comfortable taking high ownership.
Able to work in person 5 days a week in the Bay Area.
