Role & responsibilities :

Python, Advanced GenAI & Agentic Framework Concepts, Cloud Application Integration & Deployment, FastAPI Framework, Azure OpenAI Service, Retrieval-Augmented Generation (RAG), AI Agents & Tool Calling, LangGraph, LangChain, Prompt Engineering.

Key Responsibilities :

- Design and develop enterprise Generative AI solutions using Amazon Bedrock, Azure OpenAI Service, Azure AI Foundry, Grog, or AI Search Index platforms.

- Define AI solution architectures and implementation approaches aligned with business and technical objectives.

- Design and implement Retrieval-Augmented Generation (RAG), Graph RAG, and Agentic AI architectures for enterprise use cases.

- Lead development of intelligent AI agents, tool-calling workflows, and autonomous task execution frameworks.

- Design and implement multi-agent orchestration solutions using frameworks such as LangGraph and evaluate emerging frameworks such as AutoGen or CrewAI where appropriate.

- Design and optimize prompt strategies, retrieval mechanisms, context orchestration, and response generation frameworks.

- Design prompt engineering pipelines, vector database integration, semantic search solutions, and Retrieval-Augmented Generation architectures supporting enterprise AI applications.

- Design and implement workflows using LangChain or LangGraph to support scalable AI application development.

- Design scalable AI engineering architectures incorporating authentication, authorization, asynchronous processing, scheduling, multithreading, API governance, and enterprise deployment best practices.

- Lead fine-tuning and model customization initiatives to improve domain-specific AI performance.

- Define AI integration patterns and deployment approaches for enterprise application ecosystems.

- Design cloud-native AI integration patterns supporting enterprise APIs, databases, messaging platforms, and event-driven architectures.

- Establish evaluation frameworks for AI response quality, reliability, relevance, and consistency.

- Design Human-in-the-Loop (HITL) workflows and evaluation mechanisms to improve AI quality, governance, and business reliability.

- Review AI solution designs to ensure adherence to engineering standards, scalability, maintainability, and responsible AI practices.

- Troubleshoot complex AI workflow, retrieval, orchestration, and model behavior challenges through detailed root cause analysis.

- Mentor team members on GenAI frameworks, RAG architectures, agentic systems, and AI engineering best practices.

- Drive continuous improvement initiatives focused on AI solution quality, innovation, and operational effectiveness.