Description

You will design, build, and deploy scalable Generative AI systems, focusing on agentic workflows, RAG pipelines, and LLM operations.

This role is on-site.

Responsibilities

• Architect and implement Retrieval-Augmented Generation (RAG) systems using advanced techniques like hybrid retrieval, custom embeddings, and vector databases (Pinecone, FAISS, ChromaDB).
• Develop multi-agent orchestration workflows using LangGraph, LangChain, and CrewAI, incorporating routing, memory, guardrails, and failure recovery.
• Build and optimize LLMOps/MLOps pipelines with CI/CD automation, using tools like MLflow, DVC, SageMaker Pipelines, and GitHub Actions.
• Design and deploy low-latency microservices and APIs using FastAPI, Docker, and Kubernetes for scalable AI delivery.
• Implement LLM fine-tuning strategies using LoRA, QLoRA, and PEFT, and manage embedding lifecycles for semantic search.

Required Skills

• 7+ years of hands-on experience in AI, Data Science, ML, and Generative AI.
• 2+ years of strong hands-on experience with Agentic AI, VLLM, LangChain, LangGraph, RAG, and LLMOps.
• Proficiency in Python and AI/ML frameworks including PyTorch, TensorFlow, and the Hugging Face ecosystem.
• Experience with cloud-native engineering on AWS (SageMaker, Lambda, ECS/Fargate, S3, Step Functions) and GCP (Vertex AI).
• Strong experience with vector databases and semantic search technologies including Pinecone, FAISS, Weaviate, and Chroma.
• Expertise in MLOps/LLMOps practices, including CI/CD automation and scalable model deployment.
• Experience developing microservices using FastAPI, REST APIs, Pydantic, Docker, and Kubernetes.
• Hands-on experience with session and memory management for multi-agent systems and MCP tools.
• Bachelor's degree in a relevant field.

Preferred Skills

• Experience with Azure OpenAI and Azure cloud services for AI delivery.
• Familiarity with CrewAI for tool-calling, validation agents, and automated reasoning.

Key Skills

Education

Bachelor's degree