AI Harness Engineer

We’re supporting a client with the recruitment requirement outlined below. If your recruiting expertise and networks align with the role, please apply to express your interest.

Once approved to work on the opportunity, you’ll receive the full brief, including the client name, role details, and commercial terms.

Role Details

Location: San Francisco, California

Industry: AI / Scientific AI

Salary: $200,000–$300,000

Equity: Meaningful equity

Employment Type: Full-time

Work Arrangement: In-office, 5 days per week

Experience: 2–6 years

Visa Sponsorship: Yes

About the Company

An AI-native chemical manufacturing company developing a conversational chemistry platform that plans synthesis routes, engineers processes, and learns from laboratory outcomes.

The business combines AI, laboratory validation, and manufacturing capabilities, serving enterprise customers across industrial and chemical sectors. It is building a foundational AI team in the San Francisco Bay Area to develop production-grade AI systems for scientific applications.

About the Role

The AI Harness Engineer will build and own the foundational agent infrastructure powering the company's chemistry AI platform.

The central challenge is turning promising agent behavior into reliable, observable, and recoverable production systems. The engineer will develop the runtime and orchestration layer that enables AI models to plan workflows, call scientific tools, manage state, process laboratory feedback, and execute complex, long-running tasks.

This is a foundational engineering role focused on agent infrastructure and systems reliability, rather than basic model API integrations or prompt engineering.

Responsibilities

• Design and build the agent runtime, including planning, tool calls, retries, checkpoints, state management, and human handoffs.

• Represent workflows as composable, inspectable, and recoverable graphs of agents, tools, and decisions.

• Integrate scientific tools such as retrosynthesis engines, reaction databases, quantum chemistry packages, simulations, and laboratory systems.

• Build evaluation harnesses, tracing, and regression suites to measure agent performance against real scientific tasks.

• Partner with AI researchers on rollout infrastructure, trajectory collection, and reward pipelines for reinforcement learning and model post-training.

• Own production performance, including latency, cost, concurrency, caching, observability, and reliability.

• Work with chemists and product engineers to translate laboratory workflows into agent capabilities.

• Contribute to engineering standards, technical direction, mentoring, and open-source work where appropriate.

Requirements

• Strong production Python engineering skills.

• Experience independently building an agent harness, orchestration runtime, or graph-based agent framework.

• Hands-on experience with tool use, function calling, and multi-agent coordination beyond prompt templates and basic retrieval pipelines.

• Strong systems knowledge covering state management, concurrency, failure modes, idempotency, and long-running jobs.

• Experience working across model APIs, tool interfaces, and underlying infrastructure.

• Ability to design evaluations before deployment and use execution traces to identify agent failure points.

• Ability to own systems from architecture through production deployment.

Ideal Candidate Profile

• Approximately 2–6 years of relevant professional experience.

• Background in a frontier AI lab, agentic AI company, or enterprise AI environment.

• Has personally built foundational agent infrastructure rather than simply integrating existing model APIs.

• Strong production engineering skills, with the ability to work across application layers and infrastructure.

• Comfortable designing reliable systems for complex, multi-step workflows.

• Able to collaborate with researchers, engineers, and scientific domain experts.

• A master's degree or unfinished PhD is welcome; a PhD is not required.

• Chemistry experience is not mandatory, but candidates should be interested in learning the domain.

Benefits & Perks

• Health, medical, and dental coverage.

• Meaningful equity.

Interview Process

• Technical Application Interview

• Founder Screen

• Technical Leadership Interview

• Reference Checks

• Offer and Hire.