We're looking for a Generative AI Full Stack Developer to design, build, and deploy AI-powered applications for enterprise clients. You'll work across the stack from LLM orchestration and RAG pipelines to production-grade frontend and backend systems as part of client delivery teams solving real business problems with GenAI.

Key Responsibilities
Design and develop end-to-end GenAI applications, including RAG pipelines, agentic workflows, and LLM-powered features
Build and maintain full-stack applications (frontend + backend + APIs) that integrate with LLM providers and internal enterprise systems
Implement prompt engineering, fine-tuning, and evaluation frameworks to optimize model performance and output quality
Architect and manage vector databases and embedding pipelines for semantic search and retrieval
Integrate GenAI solutions with cloud platforms (Azure OpenAI, AWS Bedrock, GCP Vertex AI)
Collaborate with data engineers, solution architects, and business stakeholders to translate requirements into scalable technical solutions




Ensure responsible AI practices data privacy, bias mitigation, hallucination control, and guardrails
Write clean, tested, maintainable code and contribute to CI/CD pipelines
Support client workshops, POCs, and technical presentations as needed

Required Skills & Experience
3–6 years of skilled software development experience, with 1–2+ years hands-on with Generative AI / LLM technologies
Robust proficiency in Python (FastAPI/Flask/Django) and JavaScript/TypeScript (React, Next.js, Node.js)
Hands-on experience with LLM frameworks: LangChain, LlamaIndex, Semantic Kernel, or similar
Experience building RAG (Retrieval-Augmented Generation) systems and working with vector databases (Pinecone, Weaviate, FAISS, Azure AI Search, ChromaDB)
Familiarity with LLM APIs (OpenAI, Azure OpenAI, Anthropic Claude, AWS Bedrock, Google Gemini)
Experience with prompt engineering, fine-tuning, and model evaluation techniques

📌 Urgent Hiring Mumbai
🏢 PwC India
📍 Mumbai