Generative AI Lead

About the role

We are seeking a hands-on Generative AI Lead to design, develop, and deliver enterprise AI solutions. The ideal candidate will bring strong Python development skills, and practical expertise in building and deploying AI solutions on Azure and AWS. This role combines active development with technical leadership and customer interaction. You will own technical delivery from requirements and architecture through implementation, testing, production deployment, and ongoing support.

Location: 100% Remote. Interview Process: Two rounds of video interviews. Experience: 10+ years in IT, including 8+ years in AI/ML and 3+ years in Generative AI.

Responsibilities

• Lead the end-to-end development of Gen AI applications, including requirements gathering, solution design, coding, testing, deployment, and support.
• Write production-grade Python code to build scalable AI services, APIs, and enterprise integrations.
• Develop LLM-powered assistants, enterprise knowledge-search solutions, and AI-driven workflow automation.
• Design and implement retrieval-augmented generation (RAG) pipelines covering document ingestion, chunking, embeddings, vector search, and retrieval optimization.
• Build agentic workflows using tool calling, orchestration, error handling, and human approval where required.
• Integrate AI applications with enterprise data sources, business applications, and cloud services.
• Evaluate models, frameworks, and architecture options based on business needs, response quality, security, latency, and cost.
• Establish evaluation datasets and testing processes to assess accuracy, grounding, reliability, and performance.
• Implement safeguards for sensitive data, role-based access, prompt injection, and inappropriate data exposure.
• Work directly with customers to clarify requirements, demonstrate solutions, communicate technical trade-offs, and manage delivery expectations.
• Guide developers through architecture discussions, code reviews, troubleshooting, and technical mentorship.
• Collaborate with DevOps teams on CI/CD, deployment automation, monitoring, and production reliability.
• Maintain solution documentation, architecture diagrams, and operational support procedures.

Requirements

• 10+ years of IT experience, with substantial hands-on Python development and enterprise software delivery experience across the full SDLC.
• 5+ years of AI/ML experience, including developing, integrating, deploying, and supporting AI/ML solutions.
• 3+ years of hands-on Generative AI experience, including delivery of LLM-powered applications into production.
• 5+ years of cloud experience across Azure and AWS, covering application deployment, integration, security, monitoring, and production support.
• Strong programming skills in Python and Java including REST API development and enterprise system integration.
• Hands-on experience with Azure OpenAI, prompt engineering, structured outputs, and function/tool calling.
• Experience building RAG solutions using embeddings, vector databases or search services, and structured and unstructured enterprise data.
• Practical experience with LangChain, LangGraph, or comparable frameworks for LLM orchestration and agentic workflows.
• Experience evaluating and monitoring LLM applications using LangSmith, Langfuse, or similar tools.