Job Title : Generative AI / Vector Embeddings

Location : Remote

Experience : 7+ Years

Job Type : Full-Time / Contract (Remote)

About the Role :

We are looking for a seasoned Data Scientist with deep expertise in Generative AI, vector embeddings, and retrieval-augmented generation (RAG) to join our advanced AI and analytics team. This role will focus on building scalable, intelligent systems capable of supporting domain-specific LLM applications and knowledge integration using modern tools like Azure AI Search, LangChain, and FAISS.

You will be instrumental in designing and optimizing data pipelines, embedding strategies, and RAG workflows to ensure efficient document processing and high-quality AI responses.

Key Responsibilities :

- Design and develop data ingestion and transformation pipelines using Azure Data Lake and Cosmos DB for structured and unstructured data.

- Implement vector embedding techniques using Azure AI Search, FAISS, and LangChain to support similarity search and semantic retrieval.

- Develop and optimize RAG (Retrieval-Augmented Generation) pipelines for grounding LLM responses in domain-specific knowledge.

- Apply document chunking and intelligent metadata tagging to enhance search and response quality in LLM-driven applications.

- Integrate enterprise data and documents into knowledge bases, making them consumable by LLMs and retrieval systems.

- Monitor and optimize performance of embeddings, latency, and response quality across deployed AI systems.

- Collaborate with ML engineers and backend developers to ensure seamless integration of models and services.

Key Skills & Technologies :

- Data Engineering : Azure Data Lake, Azure Cosmos DB, Azure Data Factory

- AI Search & Embeddings : Azure AI Search, FAISS, LangChain, Sentence Transformers

- Generative AI & LLMs : Experience with OpenAI, RAG, prompt engineering

- Data Processing : Document chunking, metadata extraction, tagging, NLP preprocessing

- Knowledge Integration : Building searchable, retrievable knowledge bases

- Performance Optimization : Vector indexing, retrieval latency reduction, embedding tuning

- Programming Languages : Python (strong), SQL

- Tools : Azure ML, Git, Jupyter, REST APIs

Preferred Qualifications :

- 7+ years of experience in Data Science, with at least 2-3 years in AI/NLP/LLM projects.

- Proven experience working on production-grade RAG systems and vector database integration.

- Strong understanding of embedding models, similarity search, and large-scale data pipelines.

- Experience integrating with Azure AI stack and familiarity with LangChain frameworks.

- Ability to independently drive AI solution design, experimentation, and performance tuning.

- Strong communication and collaboration skills, especially in cross-functional, remote teams.