Remote job
Engineering Manager - AI Agents (Agent Platform, LLMs, Evals)
Job details
About this role
Role overview Lead a team building and operating production AI agents used in high-stakes financial risk workflows, including fraud, anti-money laundering, credit, and customer onboarding. This hands-on engineering leadership role combines team development with technical ownership of agent orchestration, tool use, evaluation, reliability, and observability.
Responsibilities - Lead, hire, and coach a team of roughly 5–10 engineers, setting strong technical and team practices. - Guide the design and delivery of production agent capabilities, including orchestration, tool calling, shared evaluations, guardrails, and audit trails. - Set expectations for architecture, service ownership, security, performance, reliability, and safe failure behavior. - Work with product, platform, and customer-facing engineering teams to deploy agents and turn field feedback into platform improvements. - Establish practical planning, incident response, and post-incident learning processes. - Develop senior contributors and emerging technical leaders.
Requirements - Significant software engineering experience and a record of delivering production systems. - Hands-on experience shipping production agents, including orchestration, tool calling, evaluations, and reliability engineering. - Experience managing and growing an engineering team of at least five people, including hiring and coaching. - Experience in a startup or scale-up, with the ability to work through ambiguity and introduce useful structure. - Strong technical judgment across architecture, system design, failure modes, and engineering quality. - Clear communication skills and experience working across product, data science, and distributed teams. - Experience with reliability, observability, and operations for complex AI or distributed systems.
Nice to have Experience in fintech, fraud, credit risk, anti-money laundering, compliance, or another regulated field; familiarity with MCP, multi-agent orchestration, or large-scale agent evaluation. The stated technologies include LangGraph or similar frameworks, AWS Bedrock, Python, and Java.
Benefits and work setup US-based, remote-first role. Listed offerings include salary and equity, a 401(k), health, dental, and vision coverage, unlimited paid time off, team events, and professional development opportunities.