We’re looking for an AI Lead Developer with deep expertise in Generative AI and Agentic AI systems, combined with strong architectural leadership and client engagement capabilities.
This is a high-visibility role where you’ll architect scalable GenAI platforms, lead engineering teams, manage enterprise AI engagements, and build production-grade intelligent systems powered by LLMs, RAG architectures, ReAct agents, and advanced AI workflows.
What You’ll Do
• Architect and lead development of enterprise-grade Generative AI solutions using LLMs and advanced prompting strategies.
• Design and implement Agentic AI workflows, including ReAct (Reasoning + Acting) agents and multi-agent orchestration systems using frameworks such as LangGraph and LangChain.
• Build scalable Retrieval-Augmented Generation (RAG) architectures with context engineering, evaluation pipelines, and guardrails.
• Develop and optimize advanced prompting techniques (few-shot, zero-shot, chain-of-thought, self-reflection, structured prompting, tool-augmented prompting).
• Implement structured interaction frameworks using Model Context Protocol (MCP) or similar standards.
• Develop asynchronous, distributed AI applications optimized for performance and horizontal scale.
• Design modular AI systems using microservices architecture and API-first design principles.
• Implement AI monitoring, observability, and evaluation frameworks using tools such as Langfuse (for tracing, performance monitoring, hallucination tracking, and cost analysis).
• Work closely with DevOps teams to productionize AI solutions using Docker, containerization best practices, CI/CD pipelines, and cloud-native deployment models.
• Lead client and vendor engagements as the AI technical authority — driving architecture decisions and AI solution roadmaps.
• Mentor and manage AI/ML engineering teams, setting technical standards and architectural best practices.
• Deploy and manage AI systems in Azure cloud environments (preferred).
• Develop backend AI services, APIs, and data pipelines using Python and SQL.
• Drive responsible AI practices, governance frameworks, and model lifecycle management.
