Agentic AI Engineering Lead, Enterprise Agent Orchestration

What you'll do

• Architect and build an enterprise agent orchestration platform including runtime, planner/executor loops, and memory management.
• Design multi-agent patterns for task decomposition, delegation, and deterministic fallbacks.
• Build a tool integration surface for agents to interact safely with source control, CI/CD, and internal APIs.
• Establish an evaluation and observability layer for golden datasets, regression gates, and token cost governance.
• Define the control model for AI autonomy including authorization boundaries, kill switches, and audit trails.
• Partner with Risk, Compliance, and Security teams to move agentic use cases through model governance.
• Lead and mentor a team of AI and platform engineers to deliver production-grade backend systems in Python or Golang.
• Drive enterprise adoption by defining maturity ladders, playbooks, and impact metrics for agentic use cases.

What we're looking for

• Proven experience leading AI/ML or platform engineering teams in product-focused environments.
• Strong hands-on engineering experience building and shipping production systems in Python and/or Golang.
• Demonstrated experience building production agentic AI systems including multi-agent orchestration, planning loops, and RAG pipelines.
• Experience taking an AI platform from zero to enterprise scale, including greenfield design and multi-tenant platform thinking.
• Deep knowledge of LLM engineering including prompt/context engineering, evaluation harnesses, guardrails, and cost management.
• Experience operating AI systems under strict governance with auditability, human-in-the-loop controls, and data protection.
• Proven experience with distributed systems, event-driven architectures, container-based micro-services, and cloud-native infrastructure.
• Solid grounding in CI/CD and SDLC controls using tools such as Harness, GitHub Actions, Tekton, or ArgoCD.
• Hands-on experience with DevSecOps practices and security-by-design principles.
• Experience in regulated industries like financial services with exposure to audit or model risk management (preferred).
• Exposure to policy-as-code and compliance-as-code frameworks such as OPA or Rego (preferred).
• Familiarity with LLM observability, MLOps platforms, or agent interoperability standards (preferred).