Agentic AI Or Generative AI- Lead Engineer

Experience Requirements

• 10+ years of relevant software engineering / technology experience.
• Proven experience working as a Lead Developer, Technical Lead, Senior Engineer, or equivalent hands-on technical leadership role.
• Strong hands-on experience designing and developing Agentic AI systems.
• Demonstrated experience taking AI agents and Generative AI solutions into production.
• Ability to independently operate at a senior technical level, including solution design, architecture, engineering decisions, troubleshooting, and production readiness.
• Experience designing, developing, and operating large-scale distributed systems is strongly preferred.
• Experience in platform, architecture, lead engineer, or similar senior technical roles is preferred.

Core Technical Requirements

Agentic AI

Candidate must demonstrate practical, hands-on experience with:

• Designing and developing AI agents / Agentic AI systems.
• Building AI agents that have been deployed and operated in production environments.
• Developing Agentic AI solutions beyond prototypes, proof-of-concepts, or basic chatbot implementations.
• Designing reusable Agentic AI capabilities that can support enterprise applications and multiple use cases.

Generative AI / LLM Engineering

Strong hands-on experience developing Generative AI solutions using Large Language Models (LLMs) such as:

• OpenAI GPT
• Google Gemini
• Llama or comparable enterprise LLMs

Experience should include practical development and integration of Generative AI capabilities into enterprise applications and production systems.

AI Platform & Architecture

Strong understanding and hands-on experience with:

• AI platform architecture
• API design
• Distributed systems
• Reliability engineering
• Building reusable platform components that can be consumed by multiple teams rather than developing only one-off AI applications.
• Designing scalable and maintainable enterprise AI capabilities.

Enterprise Agentic AI Patterns

Experience with enterprise AI/ML or GenAI platform capabilities, including areas such as:

• Tool and agent registry patterns
• Private registries
• Retrieval and grounding patterns
• Context management
• Memory patterns
• Context budgeting
• Production hardening
• Reusable reference implementations
• Accelerators/frameworks that enable adoption across multiple teams

AI Quality, Evaluation & Observability

Experience implementing foundations for:

• AI quality measurement
• AI/LLM evaluation practices
• AI telemetry
• Monitoring
• Reliability
• Production observability

Candidates should understand how AI solutions are evaluated and monitored after deployment, not only how models or agents are developed.

MLOps / Production Engineering

Exposure to or hands-on experience with:

• Cloud ML tooling
• Enterprise MLOps practices
• Production deployment of AI/ML solutions
• Operational monitoring and reliability
• Production hardening of Generative AI / Agentic AI solutions