Description

You will architect and deploy scalable Generative AI systems, focusing on advanced RAG pipelines and multi-agent orchestration.

This role is on-site.

Responsibilities

• Design and implement Retrieval-Augmented Generation (RAG) systems using vector databases (Pinecone, FAISS, ChromaDB) and semantic search.
• Build multi-agent orchestration workflows using LangChain, LangGraph, and CrewAI, including routing, memory, and failure recovery.
• Develop low-latency microservices and APIs with FastAPI, Pydantic, Docker, and Kubernetes.
• Establish end-to-end LLMOps/MLOps pipelines using MLflow, DVC, and GitHub Actions for CI/CD automation.
• Deploy and manage cloud-native AI infrastructure on AWS (SageMaker, Lambda, EKS) and GCP (Vertex AI).

Required Skills

• 10+ years of hands-on experience in AI, Data Science, ML, and GenAI.
• Strong proficiency in Python, PyTorch, and TensorFlow.
• Deep experience with LLM fine-tuning techniques (LoRA, QLoRA, PEFT) and Hugging Face ecosystem.
• Expertise in vector databases and embedding lifecycle management.
• Experience with AWS SageMaker, Lambda, EKS, S3, and GCP Vertex AI.
• Strong background in MLOps/LLMOps, CI/CD automation, and containerization.
• Proficiency in REST API development and microservices architecture.
• Bachelor's degree in a relevant technical field.

Preferred Skills

• Experience with Azure OpenAI and hybrid retrieval methods.
• Familiarity with session management and MCP tools in multi-agent systems.

Key Skills

Education

Bachelor's degree