Job Overview

We are seeking a highly skilled AI Engineer specializing in Large Language Models (LLMs), LangChain, RAG (Retrieval-Augmented Generation), and AI Agent/Agentic AI frameworks. The ideal candidate will work on designing, developing, and deploying advanced GenAI solutions, intelligent agents, and scalable LLM-based systems for production environments.

Key Responsibilities

Build, fine-tune, and optimize LLM-based applications for conversational AI, content generation, automation, and workflow orchestration.

Design and implement RAG pipelines using vector databases, embedding models, and retrieval frameworks.

Develop AI Agents/Agentic systems capable of autonomous task execution, tool use, memory, and multi-step reasoning.

Build end-to-end solutions using LangChain / LlamaIndex / Haystack and integrate with APIs, databases, tools, and enterprise systems.

Fine-tune open-source and proprietary models (Llama, Mistral, GPT, Claude, etc.).

Build reusable components for prompt engineering, model orchestration, and workflow automation.

Integrate LLMs with external tools (search, APIs, internal knowledge bases, automation systems).

Work with vector databases such as Pinecone, Weaviate, Milvus, FAISS, ChromaDB.

Deploy AI systems on cloud platforms (AWS, GCP, Azure) and optimize for performance, latency, and scalability.

Collaborate with product and engineering teams to deliver production-ready GenAI applications.

Required Skills & Qualifications

Strong experience with LLMs, fine-tuning, prompt engineering, and model evaluation.

Hands-on experience with LangChain, LlamaIndex, or similar orchestration frameworks.

Expertise in RAG architectures, embeddings, and retrieval optimization.

Experience building AI agents or agentic workflows using frameworks like LangChain Agents, AutoGen, CrewAI, or custom architectures.

Strong programming experience in Python with frameworks like FastAPI/Flask.

Familiarity with NLP libraries (Hugging Face Transformers, SentenceTransformers).

Experience with vector databases (Pinecone, ChromaDB, FAISS, Weaviate).

Understanding of MLOps concepts, model deployment, and monitoring.

Experience with cloud services (AWS Sagemaker, Azure ML, GCP Vertex AI).

Strong understanding of embeddings, tokenization, and text processing.