Engineering Manager (AI)

AiPrise • San Jose, CA

3d

About The Position

AiPrise is hiring an Engineering Manager to lead and grow the team building its AI agents. This is a player-coach role combining people management and hands-on engineering. The manager will hire and develop engineers while contributing to agent architectures, prompt and tool reviews, and debugging evaluations. They will own how agents are built, measured, and shipped, including their skills and tools, case-context memory, and evaluations. In the regulated KYC and KYB domain, the role prioritizes quality and observability alongside speed.

The manager will lead a team of 5–6 AI and backend engineers, oversee hiring and delivery of the AI roadmap with product, and build a culture of evaluation, learning, and accountability. They will also design and review compliance agents, build reusable agent skills, tools, and memory, own the evaluation stack, and write or review code about 50% of the time. AiPrise is a YC-backed, Series A company with approximately 60 people, building global compliance infrastructure for financial services.

Requirements

• At least 2 years of direct engineering management experience, including hiring, performance reviews, and handling at least one difficult conversation well.
• A track record of developing engineers, including supporting someone who was promoted or took on greater scope.
• Experience running team planning and delivery in a fast-moving startup or scale-up.
• At least 6 years of software engineering experience and strong backend skills in Python or TypeScript.
• Experience building and shipping LLM agents to production, and ability to explain what failed and how it was fixed.
• Practical experience designing tool- and function-calling interfaces.
• Practical experience packaging reusable skills or prompt modules.
• Practical experience implementing agent memory, including short-term context, long-term stores, and retrieval.
• Practical experience building evaluations that gate releases.
• Familiarity with at least one major model API, such as Anthropic or OpenAI, and the trade-offs between agent frameworks and plain code.
• Evidence of a measurement-oriented approach, such as an evaluation built, the metric tracked, and a decision it changed.
• Clear written communication, including the ability to explain an agent failure to compliance leads and engineers.
• Good judgment about when to build, buy, or keep a human in the loop.

Nice To Haves

• Experience in fintech, regtech, fraud, identity verification, or another regulated domain where AI decisions need an audit trail.
• Document AI experience, such as OCR, document classification, or extraction across multiple languages and formats.
• Experience with LLM observability and tracing tools, and with cost and latency optimization at scale.
• Contributions to open-source agent, evaluation, or retrieval projects, or public writing on the topic.

Responsibilities

• Manage a team of 5–6 AI and backend engineers through regular 1:1s, clear goals, feedback, and career-growth plans.
• Hire AI engineers and own the interview loop for agent-engineering roles.
• Plan and deliver the AI roadmap with product on predictable cycles while avoiding team burnout.
• Build a culture in which engineers write evaluations before claiming a win and incidents lead to fixes rather than blame.
• Design and review compliance agents, from single-document checks to multi-step investigations handed off to human reviewers.
• Build reusable skills, tools, and memory that agents use to call registries and data vendors and preserve context across a case.
• Own the evaluation stack, including golden datasets developed with compliance experts, regression tests in CI, and production monitoring.
• Write and review code about 50% of the time and select models based on accuracy, cost, and latency.

What This Job Offers

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