Technical Lead – Agentic AI Systems

• Lead the end-to-end design and deployment of agentic AI systems.
• Define and evolve AI system architecture, ensuring alignment with enterprise infrastructure and scalability requirements.
• Select and implement appropriate frameworks such as LangGraph, AutoGen, CrewAI, LlamaIndex, and others. 2. Stakeholder Collaboration
• Collaborate with cross-functional teams and stakeholders to align AI solutions with business objectives.
• Translate business needs into technical requirements and AI capabilities. 3. System Integration & Deployment
• Ensure seamless integration of agentic AI systems into existing enterprise platforms.
• Define and execute strategies for deployment, operationalization, and lifecycle management of AI agents. 4. Performance Optimization & Monitoring
• Design and implement monitoring and observability solutions for AI agents.
• Optimize performance, latency, and scalability of deployed systems.
• Implement feedback loops and evaluation frameworks to continuously improve agent performance. 5. Evaluation & Strategy
• Define and apply strategies for agent performance evaluation and LLM benchmarking.
• Stay updated with the latest advancements in LLMs, agent frameworks, and orchestration tools. Required Skills & Qualifications:
• Proven experience in implementing AI solutions for real-world enterprise problems.
  

Requirements

• Strong expertise in AI system architecture and design.
• Deep practical knowledge of Large Language Models (LLMs), Machine Learning (ML), and Agent Development.
• Hands-on experience with LLM platforms such as Gemini, GPT, LLaMA2, Mistral.
• Proficiency in agentic AI frameworks: LangGraph, Google ADK, AutoGen, CrewAI, and orchestration tools.
• Familiarity with MCP (Multi-Agent Communication Protocols) and agent-to-agent communication.
• Experience with LLM evaluation techniques and agent performance metrics.
• Strong problem-solving skills and ability to work in a fast-paced, collaborative environment. Preferred Qualifications:
• Experience working in oAshore delivery models.
• Exposure to enterprise-grade AI deployments and cloud-native architectures.
• Familiarity with DevOps/MLOps practices for AI systems.