SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
AiPrise is a YC-backed Series A company building compliance infrastructure for financial services. The company connects 800+ data sources and 80+ verification partners across 200+ countries, powering KYB, KYC, AML, sanctions screening, and ongoing monitoring for customers including Meta, Airwallex, Fireblocks, and Bridge. AI agents help compliance teams resolve more cases, catch more fraud, and scale operations without proportional headcount growth.
This is a player-coach Engineering Manager role leading the team that builds AiPrise's AI agents. You will manage 5-6 AI and backend engineers, hire the next wave of talent, run planning and delivery cycles with product, and maintain hands-on involvement in agent architecture, prompt review, and debugging. You will own how agents are built, measured, and shipped—including the skills and tools they call, context memory across cases, and evals that validate quality. In a regulated domain like KYC/KYB, agent accuracy and observability are critical; confident errors carry real audit risk and customer impact.
Key responsibilities include: managing engineers through 1:1s, goal-setting, feedback, and career development; owning the interview loop for agent-engineering roles; running predictable delivery cycles without burnout; building a culture around evals and blameless incident response; designing and reviewing compliance agents from single-document checks to multi-step investigations; building reusable skills, tools, and memory systems for registry calls and data vendor integration; owning the eval stack with golden datasets, regression tests, and production monitoring; writing code approximately 50% of the time; and selecting models based on accuracy, cost, and latency trade-offs.
REQUIREMENTS:
- 2+ years managing engineers directly, including hiring, performance reviews, and at least one difficult conversation handled well
- Track record of growing engineers: someone you managed was promoted or took on bigger scope because of your support
- Experience running planning and delivery for a team in a fast-moving startup or scale-up
- 6+ years as a software engineer with strong backend skills in Python or TypeScript
- Shipped LLM agents to production (not just prototypes); can explain what broke and how you fixed it
- Practical hands-on experience with: designing tool and function-calling interfaces; packaging reusable skills or prompt modules; implementing agent memory (short-term context, long-term stores, retrieval); building evals that gate releases
- Comfort with at least one major model API (Anthropic, OpenAI, or similar) and understanding trade-offs between agent frameworks and plain code
- Habit of measuring: can show an eval you built, the metric it tracked, and a decision it changed
- Clear written communication; ability to explain agent failures to both compliance leads and engineers
- Good judgment on when to build, buy, or keep a human in the loop
NICE TO HAVE:
- Experience in fintech, regtech, fraud, identity verification, or other regulated domains requiring audit trails
- Document AI experience: OCR, document classification or extraction across languages and formats
- LLM observability, tracing tools, cost and latency optimization at scale
- Open-source contributions to agent, eval, or retrieval projects, or public writing on the topic
