Lead AI Engineer

Position Overview:

The Lead AI Engineer is an experienced AI systems engineer working as part of a cross-functional Agile product team responsible for building and evolving McCormick's global Agentic AI platform.

This role designs and develops intelligent AI agents using Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication patterns that participate in a distributed enterprise AI ecosystem. In addition to delivering features, the AI Engineer II contributes to the evolution of platform architecture, agent orchestration patterns, retrieval strategies, and evaluation frameworks.

The position operates with a high degree of autonomy, translating loosely defined business and technical requirements into scalable, production-grade AI systems. The role requires strong system-level thinking, the ability to handle ambiguity, and a focus on reliability, performance, and maintainability within a cloud-native Azure environment.

Required Qualifications:

Level of Education and Discipline –

Bachelor's degree typically within a technical subject such as computer science.

Experience –

5–8 years of experience in software engineering, with at least 2 years focused on AI/ML or LLM-based systems in production environments.

Experience designing and deploying AI-powered applications in cloud-native Azure environments.

Demonstrated experience building RAG pipelines and working with vector databases.

Experience developing distributed, API-driven systems and integrating with enterprise platforms.

Experience working within Agile product teams delivering iterative releases.

Interpersonal Skills –

Leadership, interactions, communication, influence Excellent communication skills and a desire to collaborate openly within a fast-moving team

Other Skills and HPO Competencies -

• Hands-on experience with LangChain, LangGraph (Agents, Tools) and agent orchestration patterns.
• Practical implementation experience with MCP and A2A communication models.
• Experience with Azure OpenAI, Gemini and model integration strategies.
• Strong knowledge of Retrieval-Augmented Generation (RAG) architectures.
• Experience with vector stores such as Azure AI Search and PGVector.
• Proficiency in prompt engineering, evaluation strategies, and structured output validation.
• Experience developing RESTful APIs and integrating external services.
• Experience with Docker and containerized deployment models.
• Experience implementing CI/CD pipelines using GitHub Actions or similar platforms.
• Familiarity with feature flag strategies, telemetry, logging, and monitoring.
• Experience working with NoSQL databases and distributed system patterns.

Experience –

• Experience designing multi-agent orchestration strategies across distributed systems.
• Exposure to performance and cost optimization strategies for LLM-based systems.
• Experience contributing to shared AI platform components or reusable internal frameworks.
• Familiarity with enterprise governance, security, and responsible AI considerations.