AI Full Stack Developer (Mid-Level) – GenAI & RAG

InnoVites, who are we?

InnoVites is one of the world’s leading providers of software solutions for Cable and Wire manufacturing and distribution Industry, transforming cable factories into the smart factories.

It feels great to build and deliver software solutions that exactly address customer needs. And that’s exactly what InnoVites is about.

We have a laser sharp focus on our target market: the wire and cable industry. With our deep understanding of this vertical we love building software that creates high value for our customers.

It has resulted in continuous growth of the company, while we are serving our customers located in over 20 countries worldwide. As our customers benefit from the global energy transition, the future at InnoVites is electrifying!

As a team we cherish craftmanship and celebrate team results. Every day we seek opportunities to learn from each other and grow.

Together, we can make a difference – and you can too. Dream it. Build it. Do it here.

Job Title: AI Full Stack Developer (Mid-Level) – GenAI & RAG

Location: Chennai Type: Full-time Department: Design / Product

About the Role

We are looking for a Mid-Level AI Full Stack Developer to design, build, and deliver AI-powered product features using GenAI, RAG, and LLM integrations, alongside strong full-stack engineering.

You’ll work across frontend, backend, and AI systems to ship production-ready capabilities—not demos. You will own features end-to-end, collaborate closely with product and domain teams, and help evolve reliable GenAI workflows inside our products.

Key Responsibilities

AI, RAG & Backend (Core)

· Integrate OpenAI / Azure OpenAI / ChatGPT or similar LLMs into production systems.

· Design, build, and maintain RAG pipelines, including:

o document ingestion and preprocessing

o chunking and overlap strategies

o embedding generation

o vector indexing and retrieval

o grounding and citation approaches

· Implement context-building strategies for conversational AI:

o conversation memory handling

o dynamic context window assembly

o metadata-aware retrieval

o relevance filtering and basic re-ranking

· Build and expose AI services using FastAPI, including:

o well-defined schemas and validation

o error handling, logging, and observability

o performance and latency improvements

· Work with structured and unstructured data sources and basic preprocessing.

· Support GenAI evaluation practices (relevance, faithfulness, hallucination checks).

Full Stack Development

· Build and maintain frontend components using React / Next.js.

· Design and develop REST APIs connecting UI ↔ AI services ↔ data layers.

· Integrate SQL/NoSQL databases into AI and product workflows.

· Write clean, modular, maintainable code with testing and documentation.

Collaboration & Delivery

· Work closely with product, design, and domain experts to deliver AI-powered solutions.

· Participate in solution design, prototyping, and iterative delivery.

· Communicate clearly with technical and non-technical stakeholders.

· Take ownership of outcomes, not just tasks.

Qualifications

· 2–4 years of relevant experience (or equivalent product/project depth).

· Strong experience with Python and backend development.

· Hands-on experience building LLM / RAG-based applications.

· Solid experience with FastAPI for ML/AI service endpoints.

· Full-stack exposure across backend, frontend, and AI workflows.

· Good communication skills and a collaborative mindset.

Note: Please share GitHub / demo / portfolio links showcasing RAG + context building + FastAPI + LLM integration.

Good to Have

· JavaScript / TypeScript; React / Next.js comfort.

· Vector/search systems: FAISS, Chroma, Pinecone, Weaviate, Milvus, Elasticsearch (vector).

· Prompt engineering and context window optimization.

· Exposure to LangChain / LlamaIndex / Haystack.

· Hybrid retrieval (BM25 + vector), re-ranking, search tuning.

· RAG evaluation tooling: RAGAS, TruLens, DeepEval.

· Docker and basic cloud deployment (Azure/AWS/GCP).

· Strong SQL and data modeling fundamentals.

Why Join Us?

· Build real enterprise GenAI features inside production products.

· Work with experienced teams and deep domain experts.

· High ownership, strong engineering culture, and room to grow.

· Supportive, collaborative environment that encourages innovation.