We are looking for a Lead AI/ML Engineer Agent Developer to lead the agentic AI engineering function and drive the design, architecture, development, evaluation, and optimization of production-grade AI agents.

The role will be responsible for establishing engineering standards around LLM integration, prompt engineering, agent architecture, RAG pipelines, agent evaluation, and production performance. The ideal candidate should have strong hands-on experience building and architecting enterprise-grade LLM and AI agent solutions.

Key Responsibilities:

- Architect and establish the agent engineering framework, including orchestration patterns, prompt governance, and tool-calling standards.

- Lead technical and design reviews for AI agent implementations across the engineering team.

- Own the architecture of RAG pipelines, including embedding strategies, retrieval optimization, and accuracy benchmarking.

- Define and implement AI agent evaluation frameworks, including golden datasets, confidence scoring, hallucination testing, and regression testing.

- Establish and govern prompt engineering standards and review processes.

- Design and implement production-grade LLM and Agentic AI solutions.

- Monitor and optimize AI agent performance in production with focus on latency, cost, token usage, and accuracy.

- Mentor and guide junior AI/ML engineers in agent development, prompt engineering, RAG, and evaluation methodologies.

- Drive engineering best practices for scalable and reliable enterprise AI platforms.

- Collaborate with cross-functional teams to translate business requirements into robust AI/ML solutions.

Required Skills & Experience:

- 10+ years of experience in AI/ML Engineering.

- Minimum 5+ years of experience working with production LLM systems.

- Strong expertise in Generative AI, LLMs, Prompt Engineering, and AI Agent Development.

- Strong experience designing and architecting RAG pipelines at scale.

- Hands-on experience with Agent Evaluation, including hallucination testing, confidence scoring, golden datasets, and regression frameworks.

- Expert-level proficiency in Python.

- Experience with LLM integration and orchestration frameworks.

- Strong understanding of LLM cost management, token budgeting, latency optimization, and production performance.

- Proven experience leading or mentoring AI/ML engineering teams.

- Strong understanding of scalable AI/ML architecture and enterprise-grade AI solutions.

Good to Have:

- Experience with Model Context Protocol (MCP) or modern tool-calling standards.

- Experience building enterprise AI platforms.

- Knowledge of ITSM / IT Operations domain.

- Familiarity with TypeScript / Node.js.