Data Scientist - Generative AI

Primary Responsibilities:

- Built and implemented enterprise-level GenAI chatbots capable of natural-language search over extensive document repositories and databases.

- Research and develop multi-agentic systems for production-grade applications that handle large-scale documents and big data

- Optimize vector databases for enterprise-scale semantic search, context management, chat history, and source attribution

- Build document processing pipelines with intelligent chunking, metadata extraction, and multi-format handling

- Implement advanced retrieval strategies: hybrid search, re-ranking, and custom evaluation frameworks

- Work in AWS cloud platform for deployment - handle concurrent requests and scale

- Integrate and optimize LLMs via AWS Bedrock, or Azure with hallucination mitigation

- Debug and resolve retrieval quality issues, latency bottlenecks, and cost optimization challenges

- Opportunity to mentor and shape GenAI practices across the organization

- Individual Contributor reporting to Engineering Manager

Skills Required:

- Experience building GenAI applications from scratch including custom chunking strategies, metadata extraction, multi-format document processing pipelines, indexing, context management, memory management, fine-tuning techniques, model compression techniques, etc. (Must be able to demonstrate through technical justification and code)

- Vector database production implementation: indexing, retrieval optimization, performance tuning

- Embeddings and semantic search: sentence-transformers, similarity search, distance metrics implementation

- Advanced retrieval techniques: hybrid search (semantic + keyword), multi-stage retrieval

- Production LLM integration / hosting: context management, token optimization, streaming responses, citation systems

- Evaluation & metrics for RAG systems & chatbots

- Knowledge of deployment, monitoring, ethics, and governance principles; RESTful API development with FastAPI including error handling