Internal Acceleration, Research Engineer (Kernels)
Core
Build agentic harnesses and operating systems to accelerate the production of frontier tokens by enabling agents to conduct long-running engineering work.
Role type
Senior IC research engineer (AI agents & kernels)
Builds
Agentic harnesses, execution environments, and full-stack internal products for hardware engineering workflows.
Domain
AI infrastructure, hardware engineering, and distributed systems
Deliverable
production ML models
Required skills
Software engineering, agent design, tool design, long-context management, eval design, distributed systems, system reliability, product sense
Preferred skills
Chip development, kernels, hardware, manufacturing, infrastructure, data engineering, DevOps, fine-tuning, RAG, multi-agent orchestration
Technologies
LLMs, MCP, simulators, EDA flows, compilers, profilers
Responsibilities
Embed with kernels team to identify and solve high-leverage bottlenecks; Build and deploy LLM agents via tool-calling; Create execution environments with sandboxed access to hardware and compilers; Ship full-stack internal products from zero to one; Design evals and track adoption; Execute special projects with founders.
Seniority
Senior, hands-on IC
