Description

Design and implement generative AI models, agentic systems, and retrieval-augmented generation pipelines for enterprise workflows.

This role is on-site.

Responsibilities

• Design and build agentic AI applications using LangGraph, CrewAI, and MCP tools for multi-agent orchestration and tool-calling.
• Develop and optimize RAG pipelines using vector databases (Pinecone, FAISS, Weaviate) and semantic search strategies.
• Deploy scalable AI services and microservices using FastAPI, Docker, and Kubernetes on AWS and GCP.
• Implement LLMOps/MLOps practices including CI/CD automation, model fine-tuning (LoRA/QLoRA), and monitoring via MLflow and DVC.
• Integrate Gen AI capabilities into web applications, ensuring low-latency serving and secure enterprise operations.

Required Skills

• 10+ years of experience in AI/ML, with 7+ years hands-on in Gen AI and 2+ years in Agentic AI.
• Strong proficiency in Python, PyTorch, and TensorFlow.
• Extensive experience with LangChain, LangGraph, and agentic patterns (routing, memory, guardrails, failure recovery).
• Hands-on experience with LLMs, transformers, and the Hugging Face ecosystem.
• Expertise in cloud-native engineering on AWS (SageMaker, Lambda, EKS) and GCP (Vertex AI).
• Strong background in microservices architecture using FastAPI, REST APIs, Pydantic, and Kubernetes.
• Experience with vector databases (Pinecone, ChromaDB, FAISS) and embedding lifecycle management.
• Knowledge of MLOps/LLMOps tools: MLflow, DVC, GitHub Actions, and SageMaker/Vertex Pipelines.

Preferred Skills

• Experience with vLLM for high-throughput inference serving.
• Familiarity with Azure OpenAI services.

Referral Bonus: ₹50,000

Key Skills

Education

Bachelor's degree