Apply on Kit Job: kitjob.in/job/44mx5z

Role: Generative AI Engineer | 4–6 Years Locations: Chennai | Bangalore | Hyderabad | Pune Role Overview We are looking for a Generative AI Engineer to build, optimize, and scale production-ready AI applications. This role involves designing multi-agent systems , implementing advanced RAG pipelines , and deploying both frontier and local LLMs . If you enjoy working at the intersection of AI + backend engineering , this is a great opportunity. Tech Stack LLMs: Gemini, OpenAI, Claude, Llama, Local Models Frameworks: LangChain, LlamaIndex, Hugging Face Orchestration: LangGraph, Multi-Agent Systems (MAS) Backend: Python, FastAPI, Async Programming RAG & Data: PostgreSQL, Vector Databases, Advanced Retrieval ML/DL: PyTorch, TensorFlow, Fine-tuning Deployment: Docker, API Management, Monitoring Tools: Prompt Engineering, Workflow Design,



GenAI Optimization Key Responsibilities Design and orchestrate AI workflows using LangGraph & multi-agent architectures Build advanced RAG systems with LlamaIndex and vector databases Integrate multiple LLMs (OpenAI, Claude, Llama, etc.) based on use case Develop scalable backend services using FastAPI & Async Python Fine-tune LLMs for domain-specific improvements Optimize GenAI systems for latency, cost, and performance Deploy and manage AI services using Docker Implement monitoring, logging, and reliability practices Required Skills 4–6 years of experience in software/AI development Hands-on experience with GenAI applications in production Strong Python skills with LangChain / LlamaIndex ecosystem Experience with vector search, embeddings, and RAG pipelines Knowledge of LLM fine-tuning & local model deployment Exposure to API security, monitoring, and CI/CD pipelines Valuable to Have Experience with multi-agent systems (MAS) Knowledge of LLM optimization & cost tuning Exposure to real-time AI applications

Apply on Kit Job: kitjob.in/job/44mx5z

📌 Gen AI/ML Engineer (Nellore)
🏢 Photon
📍 Nellore