Staff Engineer, Agentic Intelligence - San Francisco

HomeVision • San Francisco, CA

7d • Hybrid

About The Position

HomeVision is seeking a Staff Engineer to own the intelligence and policy layer of their underwriting agent. This role involves designing and building the framework that translates underwriting judgment into configurable policies for an AI agent. The goal is to create an end-to-end AI underwriting platform for the mortgage industry. The engineer will work on encoding rules, ensuring policy quality, maintaining the agent's runtime environment, and establishing best practices for the team. The position emphasizes shipping quickly, learning from production data, and collaborating with ML engineers, the CTO, and senior product leadership.

Requirements

• Deeply product-oriented with a desire to engage with customers and learn new domains.
• A builder at heart with experience shipping meaningful systems used by real customers.
• Operates with urgency and ownership, moving quickly without sacrificing reliability or trust.
• Elevates people around them with strong engineering judgment, high standards, and collaborative energy.
• Excited by difficult workflow problems such as agent reliability, evaluation under ambiguity, encoding judgment as configurable policy, and AI-assisted decision-making.
• Strong engineering proficiency and ability to wield AI-powered coding tools.
• Experience building and operating LLM-based or agentic systems in production.
• Experience designing configuration-driven systems (rules engines, policy/DSL frameworks, feature-flag or config platforms).
• A rigorous, empirical approach to evaluation, with the ability to measure quality in systems where 'correct' is hard to define.
• Comfort working across the stack (Go/Python backend and TypeScript frontend).
• Track record of leading a technical surface end-to-end.

Nice To Haves

• Bonus if you’ve worked on decisioning, document understanding, or human-in-the-loop products.

Responsibilities

• Own the policy framework: Design and build the framework that turns underwriting judgment into policies the agent reasons against, structured for configuration per lender, investor, and loan product, customization for edge cases, and dynamic changes without code deployment.
• Author the policies themselves: Translate dense, real-world underwriting rules, including escalation paths and human-in-the-loop boundaries, into clear, testable policy that the agent executes reliably.
• Make policy quality measurable: Establish and tune evaluations that prove a given policy behaves correctly across messy, real loan files. Build datasets and harnesses to measure policy performance and create a fast iteration loop.
• Own the agent harness it runs in: Maintain the runtime the agent operates in, including tool use, orchestration, context management, retries, and guardrails, ensuring policies execute reliably and safely on complex, multi-step tasks.
• Elevate the team: Establish patterns, libraries, and review standards for agent and policy development. Mentor and recruit engineers.
• Ship fast and learn faster: Take capabilities from rough ideas to production in days, and rapidly iterate based on performance on real files.

Benefits

• Competitive compensation calibrated to senior/principal-level engineers in San Francisco
• Meaningful equity ownership
• Full medical, dental, and vision coverage
• 401(k) with company match
• Flexible vacation policy
• Parental leave
• Learning and professional development support

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed