Key Responsibilities :

- Lead the architecture and development of enterprise-grade agentic AI applications.

- Design multi-agent and single-agent workflows capable of reasoning, planning, decision-making, and task execution.

- Build LLM-powered applications using models such as GPT, Claude, Gemini, Llama, or equivalent.

- Develop agent orchestration, tool-calling, function-calling, memory, planning, and workflow mechanisms.

- Implement Retrieval-Augmented Generation (RAG) solutions using enterprise data sources.

- Work with vector databases and embedding models for semantic search and knowledge retrieval.

- Build integrations between AI agents and APIs, databases, enterprise applications, and external tools.

- Evaluate and optimize prompts, models, context strategies, latency, reliability, and cost.

- Establish guardrails, observability, evaluation frameworks, and safety mechanisms for AI agents.

- Lead the transition of AI prototypes into scalable production systems.

- Define technical architecture, coding standards, design patterns, and engineering best practices.

- Mentor senior engineers and guide technical decision-making across AI initiatives.

- Collaborate with product managers and stakeholders to identify high-value agentic AI use cases.

- Drive experimentation with emerging AI models, frameworks, and agentic technologies.

Required Skills :

- 10 - 20 years of overall software engineering experience with significant experience in AI/ML or GenAI engineering.

- Strong hands-on experience building LLM and GenAI applications.

- Deep understanding of agentic AI architectures and autonomous AI workflows.

- Strong Python programming and software engineering skills.

- Experience with LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, or comparable frameworks.

- Strong understanding of RAG, embeddings, vector databases, semantic search, and knowledge retrieval.

- Experience with LLM APIs, prompt engineering, function/tool calling, and structured outputs.

- Strong API and microservices development experience.

- Experience with AI evaluation, monitoring, observability, and performance optimization.

- Good understanding of cloud-native application development and scalable architectures.

- Strong system-design and problem-solving capabilities.

Good to Have :

- Experience with multi-agent systems and agent-to-agent communication.

- Experience with MCP or similar tool/context integration approaches.

- Knowledge of AI governance, responsible AI, security, and guardrails.

- Experience deploying GenAI applications at enterprise scale.

- Exposure to Kubernetes, Docker, CI/CD, and cloud platforms.

- Experience leading AI engineering teams.

Key Result Areas :

- Successful delivery of production-ready agentic AI solutions.

- Scalability, reliability, and performance of AI systems.

- Reduction in AI inference and operational costs.

- Quality and accuracy of AI-generated outcomes.

- Adoption of AI solutions across business functions.

- Technical leadership and mentoring of engineering teams.