Lead AI Engineer – Agentic AI

About the Role

We are looking for a Senior AI Agentic Lead to drive one of our most strategic enterprise client engagements — building and deploying agentic workflows at scale within a complex, large-organization engineering environment. You will be the on-site technical anchor, working directly with the client's engineering and program management teams, while leading and mentoring a global development team.

This is a hands-on leadership role — you will both build and lead. We are not looking for someone who only directs; you need to be in the code.

What You'll Do

· Serve as the primary technical point of contact for the client, embedded on-site

· Design, build, and deploy AI agent workflows across engineering and other use cases — e.g. PR review and acceleration, test generation, incident correlation & RCA, knowledge graphs, support triage, documentation refresh, etc.

· Get trained on client-specific tools, platforms, and engineering processes, then cascade that knowledge to the Global team

· Lead sprint-based delivery across a distributed team — setting technical standards, reviewing outputs, and unblocking issues

· Collaborate with the client's stakeholders to define scope, validate agent outputs, and iterate quickly

· Work closely with other members of the team to incorporate platform knowledge into agent design

· Identify automation opportunities across the developer journey and translate them into well-scoped, executable agent implementations

· Operate the AI Agentic CoE governance cadence — daily team sync, weekly KPI review, monthly steering with client sponsors

What We're Looking For

· 10 years software engineering, 2–3 years focused on AI / LLM-based systems

· Must be hands-on — actively building, coding, deploying, not just directing

· Proven experience designing and building agentic systems — multi-step reasoning, tool use, memory, orchestration

· Strong proficiency with Claude (Anthropic API / Claude Agent SDK) and familiarity with other LLM providers (OpenAI, open-weight Llama / Mistral, cloud-native model platforms)

· Agentic frameworks — LangChain, LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, or similar

· Python proficiency; APIs, data pipelines, workflow automation

· Production LLM patterns — RAG, evaluations, guardrails, structured outputs, function calling, prompt engineering

· Enterprise client work — translating ambiguous requirements into working systems

· Distributed team leadership (US offshore)

· Strong communication skills

Nice to Have

· Developer-platform / DevEx / SRE / observability engineering background

· Identity / IAM / fraud / trust-and-safety domain exposure

· Familiarity with enterprise tooling ecosystems (ticketing, dashboards, service graphs, deployment tools, observability stacks)

· Prior consulting or embedded-engagement experience

· Fintech, SaaS, or large-scale consumer-product engineering exposure

What Makes This Role Unique

You will be working within one of the most sophisticated engineering environments in the technology industry, with direct access to the client's senior engineering leadership. The problems are real, the scale is significant, and the agents you deploy will be in active production use across an organization that touches tens of millions of customers.