Senior Associate

Only candidates currently available in Kolkata are preferred

GenAI Engineer Roles & Responsibilities

• Design, develop, and deploy Generative AI solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI Agents.
• Develop enterprise-grade GenAI applications using Python, LLM APIs, LangChain/LangGraph, and other AI/ML frameworks.
• Build and optimize RAG pipelines including document ingestion, preprocessing, chunking, embeddings, vector search, retrieval, reranking, and response generation.
• Work with vector databases such as FAISS, Pinecone, Azure AI Search, and PostgreSQL/pgvector for semantic search and knowledge retrieval.
• Develop prompt engineering strategies including system prompts, few-shot prompting, structured outputs, and prompt optimization.
• Integrate LLMs with enterprise applications, REST APIs, databases, and external/internal tools using function calling and tool-based workflows.
• Design and implement AI Agents capable of reasoning, tool selection, task execution, and multi-step workflow orchestration.
• Develop APIs and backend services using Python and frameworks such as FastAPI or Flask.
• Evaluate and improve LLM and RAG performance based on accuracy, relevance, hallucination rate, latency, and cost.
• Implement LLM evaluation frameworks, test datasets, monitoring, logging, and performance metrics for production GenAI applications.
• Work with cloud-based AI services including Microsoft Azure, Azure OpenAI, AWS, or Google Cloud for deploying scalable GenAI solutions.
• Implement responsible AI, security, and governance practices including data privacy, access control, prompt-injection protection, and prevention of sensitive-data leakage.
• Collaborate with data scientists, software engineers, architects, business teams, and clients to understand requirements and translate business problems into scalable AI solutions.
• Participate in solution architecture, proof-of-concepts (PoCs), technical design, development, testing, deployment, and production support.
• Optimize LLM applications for scalability, performance, token consumption, response time, and infrastructure cost.
• Stay updated with emerging technologies in Generative AI, LLMs, multimodal AI, AI Agents, model fine-tuning, and enterprise AI.
• Contribute to technical documentation, code reviews, development standards, and best practices for GenAI solutions.

Key Skills

Python | Generative AI | LLM | RAG | Prompt Engineering | AI Agents | LangChain | LangGraph | OpenAI | Azure OpenAI | Embeddings | Vector Databases | Semantic Search | NLP | FastAPI | REST APIs | SQL | Azure | AWS | Docker | Git | LLM Evaluation | Responsible AI