Job Title: Full-Stack Engineer (Python & Generative AI)
Role Overview
We are seeking a talented and driven 4 to 6 years of Full-Stack Engineer with deep expertise in Python and Generative AI to design, build, and deploy production-grade AI-powered applications . In this role, you will bridge the gap between complex artificial intelligence models and intuitive, user-facing experiences.
You will own the end-to-end development of advanced chatbot interfaces, conversational agents, and data retrieval systems leveraging Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) . The ideal candidate thrives at the intersection of robust backend infrastructure, slick user interfaces, and bleeding-edge AI orchestration.

Key Responsibilities
AI Orchestration & Development: Design, implement, and maintain advanced RAG pipelines , including document ingestion, chunking strategies, semantic search, and vector database optimization.
Backend Systems: Architect and build scalable, secure, and high-performance APIs and microservices using Python frameworks (e.g., FastAPI, Flask) to orchestrate LLM workflows and handle complex application logic.
Frontend Engineering: Develop responsive, accessible, and intuitive UI components for chatbots, interactive dashboards, and AI copilots using modern frontend technologies (e.g., React, Next.js, or Vue.js).
Agentic Frameworks: Implement agent-based architectures and multi-step conversational context management using orchestration tools like LangChain, LangGraph, or LlamaIndex .
Performance & Reliability: Evaluate, version, and optimize prompt engineering templates to reduce hallucinations, cut system latency, and balance API runtime costs.
Data & Infrastructure Management:



Design schemas and optimize performance across relational databases (PostgreSQL/MySQL), NoSQL, and vector databases (e.g., Pinecone, Chroma, Milvus, Qdrant, PGVector).

Required Skills & Qualifications

1. Backend & AI Layer
Core Language: Advanced proficiency in Python (async programming, multiprocessing, error handling, and object-oriented design).
Frameworks: Hands-on experience with FastAPI, Flask, or Django .
Generative AI & LLMs: Demonstrated experience integrating foundational models from major providers (OpenAI, Anthropic, Google, Azure) or hosting open-source variants (Llama, Mistral).
RAG Expertise: In-depth knowledge of embeddings, hybrid search (BM25 + dense search), cross-encoders, reranking , and context window optimization.

2. Frontend Layer
Languages & Tooling: Strong fundamentals in JavaScript/TypeScript, HTML5, and CSS3 .
Frameworks: Extensive experience with React.js, Next.js , or similar up-to-date frameworks.
State Management: Experience managing continuous state streaming (such as Server-Sent Events/WebSockets) for real-time chatbot response streaming.

3. DevOps, Cloud & Databases
Databases: Comfort with both structured SQL and specialized vector stores .
Cloud & Containers: Experience deploying AI applications on cloud providers ( AWS, GCP, or Azure ) using Docker containers.
CI/CD: Proficient with Git and automated testing/deployment workflows.

Nice-to-Have Skills
Familiarity with LLM evaluation frameworks (e.g., Ragas, TruLens).
Experience with fine-tuning open-source LLMs or parameter-efficient tuning techniques (LoRA/QLoRA).
Familiarity with the Model Context Protocol (MCP) and tool-calling paradigms.
Background in developing voice-enabled AI assistants or multimodal

📌 Full Stack Developer (Python & Vue.js) (Mumbai)
🏢 ReBIT | Reserve Bank Information Technology
📍 Mumbai