Lead Product Manager, Agent Platform

Agents are starting to do a lot of the work in mortgage, both at Pylon and at our customers. We're hiring a Lead PM to own the Agent Platform, which is what every Pylon agent is built on and how outside agents work with Pylon. The job has two halves: an internal half, building the tools and infrastructure engineers, operators, and business teams use to build, test, ship, and monitor agents; and an external half, making Pylon the easiest place for customers' agents to do real work, including MCP servers, agent-oriented APIs, and the permissions and guardrails that keep it safe. Compliance is non-negotiable. We don't expect you to be a mortgage expert on day 1, but over time you'll need to become one of the most trusted mortgage experts on the team.

Responsibilities

Set the direction for agents across Pylon and align product, engineering, and operations on where they will make the biggest difference; Own the roadmap for the platform's core pieces, like tools, orchestration, context and memory, retrieval, evals, observability, and guardrails; Make it much faster for internal teams to go from an idea to an agent running in production, and provide shared patterns; Treat evals as a product, with shared datasets, benchmarks, regression checks, and human review where a regulated decision needs it; Own how external agents work with Pylon, including MCP servers, APIs, scoped permissions, rate limits, and docs for people and LLMs; Make sure every agent action can be traced and explained; Make build or buy calls on models, vector databases, frameworks, and vendors, while monitoring cost, latency, and quality; Write and ship code, commit to the codebase, and build agents on the platform; Work with GTM and Account Management to help customers connect their agents to Pylon, support deals, and ensure customer success; Help hire and grow the team as the platform scales

Requirements

4+ years as a product manager; An engineering background is a plus; Owned and scaled a developer platform, infrastructure product, or API used by several teams or outside customers; Shipped LLM-based agents or agent tooling to production and knows tool use, MCP, multi-agent orchestration, and structured outputs; Knows evals well, including golden datasets, LLM-as-judge, and regression testing, and can connect model quality to business results; Understands retrieval, including RAG, embeddings, vector databases, chunking, hybrid search, and reranking; Understands tradeoffs between prompt and context engineering, model choice, and fine-tuning, and how each affects cost, latency, and accuracy; Familiar with tracing, guardrails, prompt injection, and protecting sensitive data like borrower PII; Writes code and is comfortable committing to a production codebase, building prototypes, and going deep on architecture with engineers; Has built 0-1 enterprise software in a regulated industry; Can write SQL and define metrics showing whether agents are working and whether teams are using the platform; Must live in or be willing to relocate to Palo Alto (CA) or New York City

Nice to have

Mortgage or fintech infrastructure experience; Work on document understanding (OCR, extraction, classification)