Data Scientist - RAG/LLM

Description :

Role & responsibilities :

Associate Software Engineer Data Scientist

Job Level : Data Scientist

Experience Level : 5+

Location : Pune (Hybrid)

Reporting To : Data Science and Knowledge Engineering Manager

What we do :

As a global leader with 130+ years of legacy in smart, healthy and sustainable buildings, our mission is to reimagine the performance of buildings to serve people, places and the planet. Join a winning team that enables you to build your best future! Our teams are uniquely positioned to support a multitude of industries across the globe. You will have the opportunity to develop yourself through meaningful work projects and learning opportunities. We strive to provide our employees with an experience, focused on supporting their physical, financial, and emotional wellbeing.

We are a Great Place to Work Certified organization. Become a member of the Johnson Controls family and thrive in an empowering company culture where your voice and ideas will be heard - your next great opportunity is just a few clicks away!

What We Offer :

- Opportunities to work on real-world projects and cutting-edge technologies.

- A collaborative and inclusive work culture.

- Opportunity to work on enterprise-scale Generative AI and RAG solutions

- Exposure to cutting-edge LLM, agentic AI, and cloud-native architecture

- Collaborative, inclusive, and innovation driven work culture

- Learning and growth through real-world, high-impact AI projects

- Cross-functional collaboration with product, engineering, and domain teams

Job Description :

We are looking for a skilled and motivated Data Scientist - Generative AI to join our Data Science and Knowledge Engineering team. This role focuses on designing, building, and deploying LLM-powered and Retrieval-Augmented Generation (RAG) solutions to solve complex enterprise and domain-specific problems.

The ideal candidate will combine strong data science fundamentals with hands-on experience in LLMs, embeddings, vector search, and prompt engineering, and will contribute to production-grade GenAI systems.

What will you enjoy doing :

- Design, build, and maintain RAG pipelines integrating document stores, vector databases, and LLMs

- Develop LLM-powered applications for question answering summarization, search, and decision support

- Implement document ingestion, chunking, embedding, retrieval, and reranking strategies.

- Apply prompt engineering, system prompting, and evaluation techniques to improve relevance and grounding

- Build and track LLM quality metrics such as relevance, faithfulness, latency, and cost

- Collaborate with product managers, engineers, and domain experts to translate business needs into GenAI solutions

- Support agentic workflows, tool usage, and multi-step reasoning pipelines where applicable

- Apply responsible AI practices, including hallucination mitigation, guardrails, and security controls

- Assist in deploying, monitoring, and iterating GenAI solutions in production environments

Key Responsibilities :

- Collaborate with cross-functional teams to design, develop, and Gen AI solutions

- Experience in using LLMs, robust prompting strategies, and its relevant frameworks.

- Good Experience with Lang Graph, Microsoft Agent Framework, llama index, etc.

- Apply Machine Learning, NLP, Deep Learning and GenAI functionalities to solve problems

- Develop and maintain user interfaces using react or any similar UI framework.

- Utilize Azure for cloud-based application development and deployment.

- Identify, troubleshoot, and debug issues to ensure high-quality deliverables.

- Continuously learn and adapt to new tools, technologies, and best practices.

- Apply strong problem-solving skills to deliver innovative and effective solutions.

- Proven work experience on using deep learning frameworks such as TensorFlow, Pytorch, etc.

- Proven work experience with cloud platforms like Azure is a must.

- Working knowledge of Azure DevOps, GitHub, Docker is good to have.

- Experience with Search Indexes (SOLR, Elastic Search, Redis, Azure Cognitive Search, etc.) and Search concepts are plus.

Qualifications and Skills :

Required :

- Bachelors or masters degree in computer science, Data Science, AI, or related field

- Strong proficiency in Python for data science and GenAI development

- Hands-on experience with Large Language Models (LLMs) (Azure OpenAI / OpenAI or equivalent)

- Solid experience building Retrieval-Augmented Generation (RAG) systems

- Strong understanding of embeddings, vector similarity search, and semantic retrieval

- Experience with prompt engineering, few-shot prompting, and response evaluation

- Working knowledge of SQL / NoSQL and unstructured data processing

- Strong analytical, problem-solving, and communication skills

- Ability to work effectively in cross-functional and ambiguous environments

Preferred :

- Experience with LangChain, Semantic Kernel, LlamaIndex, or similar frameworks

- Hands-on experience with vector databases (Azure AI Search, Pinecone, FAISS, etc.)

- Exposure to Agentic AI, tool orchestration, or multi-agent systems

- Experience with cloud-native deployments (Azure preferred)

- Familiarity with LLMOps / MLOps, monitoring, and cost optimization

- Domain experience in enterprise, industrial, or technical knowledge systems