Senior AI Engineer, Agents

ChipAgents•San Jose, CA

3d•$250,000 - $350,000•Onsite

About The Position

ChipAgents is revolutionizing chip design and verification with agentic-AI workflows. Founded by experts in AI and semiconductor design, we partner with top-10 semiconductor companies, hyperscale cloud providers, and cutting-edge startups. Our platform accelerates RTL development, functional verification, and simulation, unlocking new levels of productivity and design quality. We are hiring Software Engineers to improve the performance, reliability, and efficiency of AI agents for hardware applications. You'll identify failure modes, design and run evaluations, develop new agent capabilities, and turn successful experiments into production software. You'll join a sizable, rapidly growing team of software engineers, researchers, hardware experts, customers, and founding and field teams, working across customer discovery, evaluation design, applied research, product development, and deployment for a broad range of hardware-engineering problems.

Requirements

5+ years of software engineering experience, with a track record of shipping and operating complex, large-scale production services.
Strong backend engineering skills, with ownership of system architecture, scalability, reliability, performance, and cost.
Hands-on experience building production agent harnesses, including tool execution, context management, orchestration, durable state, and failure recovery.
Ability to diagnose agent failures and turn experimental capabilities into reliable, customer-ready services.
Strong programming skills in Python and/or TypeScript, with high standards for code quality, testing, and maintainability.
Clear communication and strong ownership across engineering, research, product, and customer-facing teams.
Ability to set architectural direction, lead cross-team initiatives, and mentor engineers while remaining hands-on.

Nice To Haves

Experience building agent memory systems, including persistent memory, retrieval, and context compression.
Experience building agent evaluations, including reproducible environments, automated grading, and regression detection.
Experience validating and calibrating LLM-as-a-judge evaluations against human judgments or verifiable outcomes.
Experience optimizing agents through systematic experimentation to improve task success, reliability, latency, or cost.
Interest in chip design, EDA, RTL, or hardware-software systems.

Responsibilities

Identify failure modes in AI agents and design and run evaluations to measure and improve their performance, reliability, and efficiency.
Develop new agent capabilities and turn successful experiments into production software.
Design effective evaluations based on interactions with customers and domain specialists.
Analyze traces and experimental results to identify bottlenecks.
Develop tool interfaces, context-management systems, memory, and multi-step or multi-agent orchestration.
Form clear hypotheses, test ideas quickly, and distinguish meaningful improvements from benchmark noise.
Move between experimental work and pragmatic product engineering as needed.
Write well-architected, maintainable production code.