Engineering Manager (AI)

Description

The company is YC-backed, at Series A, and builds compliance infrastructure for financial services worldwide. Its customers include banks, fintechs, cross-border payment providers, stablecoin and crypto firms, and marketplaces, which get a full picture of every business they onboard, wherever it is based.

One integration gives access to 800+ data sources and 80+ verification partners in 200+ countries. It covers KYB, KYC, AML, sanctions screening and ongoing monitoring for customers such as Meta, Airwallex, Fireblocks and Bridge.

The company's AI agents let compliance teams resolve more cases, catch more fraud and scale their work without adding headcount.

The company has about 60 people.

The role is for an Engineering Manager who will lead the team building these AI agents. It is a player-coach position: you manage and grow engineers, and you stay hands-on enough to design agent architectures, review prompts and tool definitions, and debug a failing eval yourself.

You will decide how the agents are built, measured and released, including the skills and tools they call, how they keep context across a case, and the evals that show whether a change helped or hurt. In KYC and KYB work, an agent that is confidently wrong creates financial and audit risk for customers, so quality and observability matter as much as speed.

Responsibilities

• Manage a team of 5-6 AI and backend engineers through weekly 1:1s, clear goals, direct feedback and career plans.
• Hire new AI engineers, own the interview process for agent engineering roles and raise its standard.
• Plan and run delivery for the AI roadmap with product, so the team ships on a predictable schedule without burning out.
• Encourage a culture where engineers write evals before claiming a improvement, and where incidents lead to fixes rather than blame.
• Design and review the compliance agents, from single document checks to multi-step investigations that pass cases to human reviewers.
• Build reusable skills, tools and memory that let agents query registries and data vendors and carry context through a case.
• Own the eval stack: golden datasets built with compliance experts, regression tests in CI and monitoring in production.
• Write and review code about 50% of your time, and pick models based on accuracy, cost and latency.

Requirements

• Have 2+ years of direct experience managing engineers, including hiring, performance reviews and at least one difficult conversation you handled well.
• Have a record of helping engineers grow, such as someone you managed being promoted or taking on a larger scope with your support.
• Have run planning and delivery for a team at a fast-moving startup or scale-up.
• Have 6+ years as a software engineer with strong backend skills in Python or TypeScript.
• Have built and shipped LLM agents to production, not just prototypes, and can explain what failed and how you fixed it.
• Have hands-on experience designing tool and function-calling interfaces, packaging reusable skills or prompt modules, implementing agent memory (short-term context, long-term stores, retrieval) and building evals that gate releases.
• Be comfortable with at least one major model API, such as Anthropic or OpenAI, and understand the trade-offs between agent frameworks and plain code.
• Measure your work: you can show an eval you built, the metric it tracked and a decision it changed.
• Communicate clearly in writing. You can explain an agent failure to a compliance lead and to an engineer.
• Use good judgment about when to build, when to buy and when to keep a human in the loop.
• Have experience in fintech, regtech, fraud, identity verification or another regulated domain where AI decisions need an audit trail.
• Have document AI experience with OCR, document classification or extraction across many languages and formats.
• Have experience with LLM observability and tracing tools, and with cost and latency optimization at scale.
• Have contributed to open-source agent, eval or retrieval projects, or written publicly on these topics.