GenAI & Agentic AI

You will be responsible for building, optimizing, and deploying AI-driven solutions that solve real-world business problems at scale. Key Responsibilities Design & Develop GenAI Applications: Build scalable AI applications using Python, integrating LangChain, LangGraph, MCP, and AgentOps frameworks. LLM Integration: Work with multiple LLM providers (Azure AI, AWS Bedrock, OpenAI, Anthropic, etc.) for text, multimodal, and agent-based workflows.

RAG Implementation: Architect and deploy Retrieval-Augmented Generation pipelines, integrating vector databases and knowledge graphs. Fine-tuning & Model Ops: Fine-tune LLMs for domain-specific tasks, implement MLOps pipelines for continuous integration, testing, and monitoring. Agentic AI Development: Design multi-agent systems with task orchestration, memory handling, and error recovery.

Deployment & Cloud Infrastructure: Deploy applications on AWS cloud (EC2, Lambda, S3, Bedrock, SageMaker, etc.) and Azure AI services . Performance Optimization: Ensure model efficiency, latency reduction, and cost optimization in production environments. Collaboration: Work closely with cross-functional teams (Data Scientists, DevOps, Product Owners) to deliver high-quality AI solutions.

Required Skills & Qualifications Strong proficiency in Python with experience in backend development. Hands-on experience with GenAI frameworks : LangChain, LangGraph, MCP, AgentOps. Knowledge of RAG (Retrieval-Augmented Generation) pipelines and vector databases (Pinecone, Chroma, Weaviate, FAISS).

Experience in fine-tuning and prompt engineering for LLMs. Strong understanding of MLOps (CI/CD for ML, model deployment, monitoring). Experience with cloud AI platforms : Azure AI, AWS Bedrock, AWS SageMaker, GCP Vertex AI (preferred).

Knowledge of Agentic AI concepts – multi-agent orchestration, planning, memory. Familiarity with Docker, Kubernetes, Terraform, and GitOps practices. Strong problem-solving and debugging skills.