Job Summary :

We are seeking an experienced Data Scientist with experience in designing, developing, and deploying enterprise-scale Generative AI solutions. The ideal candidate will have expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), prompt engineering, Natural Language Processing (NLP), and cloud-based AI platforms such as Microsoft Azure OpenAI or OpenAI. The role involves building scalable AI-powered applications, optimizing model performance, and collaborating with cross-functional teams to deliver innovative AI solutions.

Key Responsibilities :

- Design, develop, and deploy enterprise-grade Generative AI and LLM-based applications.

- Build Retrieval-Augmented Generation (RAG) pipelines to enhance AI responses using enterprise knowledge sources.

- Develop AI-powered applications using OpenAI, Azure OpenAI, and other LLM platforms.

- Implement prompt engineering techniques to improve model accuracy, reliability, and response quality.

- Evaluate, benchmark, and optimize LLM performance using automated evaluation frameworks and human feedback.

- Develop intelligent AI workflows using frameworks such as LangChain, LlamaIndex, Semantic Kernel, or similar orchestration frameworks.

- Integrate vector databases such as FAISS, Pinecone, ChromaDB, Weaviate, or Milvus for semantic search and knowledge retrieval.

- Collaborate with data engineers to build scalable data pipelines and AI integration workflows.

- Deploy, monitor, and optimize AI applications on Microsoft Azure and cloud-native environments.

- Implement Responsible AI practices, including PII protection, content moderation, hallucination mitigation, and AI governance.

- Develop REST APIs and backend AI services using Python frameworks such as FastAPI or Flask.

- Monitor application performance, troubleshoot production issues, and continuously improve AI system reliability.

- Stay up to date with advancements in Generative AI, LLMs, NLP, and emerging AI technologies.

Required Skills :

- 5+ years of experience in Data Science, Machine Learning, or Artificial Intelligence.

- Strong proficiency in Python and SQL.

- Hands-on experience with Large Language Models (LLMs), Generative AI, and Natural Language Processing (NLP).

- Experience developing AI solutions using OpenAI, Microsoft Azure OpenAI, or similar LLM platforms.

- Strong expertise in Retrieval-Augmented Generation (RAG) architecture and implementation.

- Experience with LangChain, LlamaIndex, Semantic Kernel, or similar AI orchestration frameworks.

- Hands-on experience with vector databases such as FAISS, Pinecone, ChromaDB, Weaviate, or Milvus.

- Knowledge of prompt engineering, LLM evaluation, fine-tuning concepts, and AI model optimization.

- Experience developing backend APIs using FastAPI, Flask, or similar Python frameworks.

- Familiarity with Azure AI services, Azure Machine Learning, Azure AI Foundry, or cloud-native AI deployments.

- Knowledge of machine learning frameworks such as PyTorch, TensorFlow, Scikit-learn, or Hugging Face Transformers.

- Experience with Docker, Git, CI/CD pipelines, and Agile development methodologies.

- Strong understanding of Responsible AI, data privacy, AI governance, and security best practices.

- Excellent analytical, communication, and stakeholder management skills.