GenAI Developer

We are looking for a GenAI Developer with 2-4 years of experiencein building AI-powered applications using Large Language Models (LLMs). The ideal candidate should have hands-on experience developing Retrieval-Augmented Generation (RAG)applications, AI Agents, Vector Databases, and orchestration frameworks such as LangChain or LangGraph. You will work closely with AI Engineers, Data Engineers, and Product teams to build scalable, production-ready AI solutions for enterprise marketing, customer engagement, and decision intelligence platforms.
Responsibilities:
Design, develop, and deploy enterprise-grade Generative AI applications.
Build Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models.
Develop AI Agents capable of reasoning, tool calling, workflow automation, and multi-step task execution.
Build and orchestrate AI workflows using LangChain, LangGraph, or similar frameworks.
Integrate Large Language Models (OpenAI, Anthropic, Gemini, Llama, etc. ) into production applications.
Design and optimise vector search pipelines using modern Vector Databases.
Evaluate, monitor, and optimise LLM performance, latency, accuracy, and cost.
Participate in architecture discussions and contribute to the design of scalable AI platforms.
Requirements:
2-4 years of software development experience, with hands-on experience in Generative AI.
Strong proficiency in Python.
Hands-on experience building Retrieval-Augmented Generation (RAG)applications.
Experience with LangChain, LangGraph, CrewAI, AutoGen, or similar orchestration frameworks.
Strong understanding of AI Agents, tool calling, function calling, and agent workflows.
Experience working with vector databases such as Pinecone, Weaviate, Qdrant, ChromaDB, FAISS, or Milvus.
Strong understanding of embeddings, semantic search, and document retrieval.
Experience integrating APIs and LLM providers such as OpenAI, Azure OpenAI, Anthropic Claude, Gemini, or open-source models.
Good understanding of prompt engineering, structured outputs, and LLM evaluation.
Strong problem-solving and analytical skills.
Preferred Skills:
Experience with NVTabular and feature engineering pipelines.
Experience with PyTorch, TensorFlow, or Hugging Face Transformers.
Experience building REST APIs using FastAPI or Flask.
Good to Have:
Strong passion for Artificial Intelligence and emerging GenAI technologies.
Ability to design scalable, production-ready AI systems rather than just prototypes.
Curiosity to experiment with new LLM frameworks and agent architectures.
Strong debugging and problem-solving abilities.
Excellent communication and collaboration skills.
Ability to work in a fast-paced, innovation-driven environment.
Immediate joiners preferred.

Experience
2-5 yrs