Lead AI Engineer - Agentic Supply Chain Systems

Role and Responsibilities

• Build agentic supply-chain systems: Design, implement, and maintain agent workflows that support forecasting, order management, inventory planning, discrepancy detection, and operational recommendations.
• Own agent orchestration: Build a central orchestration layer that routes tasks, coordinates multiple agents, manages tool and data-source access, and provides a clear user-facing interface.
• Integrate with enterprise data systems: Connect agentic workflows to ERP data lakes, Lake House architectures, APIs, and existing AWS-hosted infrastructure.
• Operate beyond prototypes: Ensure systems work on real production data and continue to perform under realistic scale, latency, reliability, and maintenance constraints.
• Optimize production behavior: Monitor and improve token usage, agent routing, memory use, cost efficiency, scalability, and long-term sustainability.
• Strengthen security: Implement prompt-security strategies, safe tool execution, access boundaries, and guardrails that prevent system hijacking, accidental destructive actions, or unsafe data loading patterns such as loading entire data sets into agent memory.
• Use structured data contracts: Apply Pydantic models and validated input/output schemas so multi-agent systems remain predictable, typed, and auditable.
• Create evaluation into the system: Develop benchmarks, regression checks, reliability tests, and model-upgrade evaluations that track accuracy and behavior over time.
• Lead through knowledge: Act as a senior IC, mentor, coach, and point of contact for agentic AI guidance across the project and occasionally across other teams.
• Upskill the team: Help junior AI engineers and adjacent engineering teams understand agentic-system design, limitations, risks, and production practices.

About You

• Significant production experience building, running, and maintaining large agentic AI systems.
• Hands-on experience with Google ADK, LangChain, or LangGraph. Google ADK is preferred, and strong LangChain or LangGraph experience is also highly relevant.
• Strong Python skills. Node.js experience is acceptable where supported by deep agentic-system expertise.
• Strong understanding of Lake House architecture and enterprise data-platform integration.
• Knowledge of MCPs, data-source orchestration, tool access patterns, and safe interaction with external systems.
• Experience optimizing token usage and identifying inefficient or risky agent execution paths.
• Experience with prompt injection risks, prompt security strategies, permissions, guardrails, and production safety patterns.
• Experience using Pydantic or similar structured validation approaches for reliable agent input and output.
• Knowledge of evaluation approaches for agentic applications, including small benchmarks, regression testing, reliability checks, and model-upgrade tracking.
• Familiarity with AI coding agents such as Claude or Cursor, including their practical limitations and how to use them efficiently.
• Excellent communication skills and the ability to lead through expertise, mentoring, and clear technical guidance.
• Fluent English and comfort working in an international, remote-first team.
• EU residency and permission to work in the EU.

Nice to Have

• Experience with Microsoft Fabric or Databricks.
• Strong experience with Snowflake, AWS Redshift, or Google BigQuery.
• Familiarity with AWS Bedrock and Bedrock Agent Core evaluation features.
• Experience with supply-chain systems, forecasting, order management, inventory planning, or discrepancy-monitoring workflows.
• Experience designing dashboard-based AI interfaces for operations teams.
• Experience mentoring junior AI engineers or acting as a technical point of contact across multiple teams.

Technologies & Tools You May Work With

• Python
• Node.js
• Google ADK
• LangChain
• LangGraph
• MCP
• Pydantic
• AWS
• AWS Bedrock
• Lake House architectures
• Microsoft Fabric
• Databricks
• Snowflake
• AWS Redshift
• Google BigQuery
• ERP data lakes
• Supply-chain APIs
• AI coding agents such as Claude or Cursor