Role Overview :

We are looking for an experienced AI/LLM Engineer to design, build, and maintain intelligent applications powered by Large Language Models (LLMs), embeddings, similarity search, vector databases, and multi-agent architectures.

Key Responsibilities :

- Design and implement embedding pipelines for text, documents, images, and structured data.

- Build and optimize semantic search and similarity search systems using vector databases (Pinecone, Weaviate, Milvus, FAISS, Chroma, OpenSearch).

- Develop LLM-powered applications including chatbots, Q&A systems, recommendation engines, and autonomous agent workflows.

- Implement RAG (Retrieval Augmented Generation) pipelines with hybrid retrieval and reranking.

- Design and develop multi-agent architectures (planner-executor, supervisor-worker, tool-using agents).

- Build and deploy MCP (Model Context Protocol) servers to expose tools, memory, and external systems.

- Develop structured agentic workflows using frameworks like LangGraph or similar orchestration engines.

- Implement multi-agent communication using A2A protocols.

- Fine-tune prompt strategies, memory handling, and system prompts.

- Integrate LLM providers (OpenAI, Azure OpenAI, Anthropic, Google Gemini, Meta LLaMA, Mistral).

- Build APIs and microservices using Python, Java, or Node.js.

- Implement AI safety mechanisms, hallucination reduction, and evaluation pipelines.

Tech Stack & Requirements :

- 5+ Years overall experience, with 1+ year in building Agentic AI.

- Strong proficiency in Python, Java, or TypeScript.

- Hands-on experience with LangChain, LlamaIndex, Semantic Kernel, or Spring AI.

- Experience with vector databases and RAG architectures.

- Experience with Docker, Kubernetes, and CI/CD pipelines.

- Experience deploying AI workloads on AWS, Azure, or GCP.