Job Title: Data Scientist
Job Description:
• Design, build, and maintain production -grade AI systems using Large Language Models (LLMs)
• Develop and implement RAG (Retrieval -Augmented Generation) architectures
• Design effective prompting strategies, grounding techniques, and few -shot examples
• Build vector search and hybrid retrieval pipelines with re -ranking and metadata filtering
• Process unstructured data from PDFs, DOCX, HTML, and OCR sources
• Perform data cleaning, normalization, and preparation for chunk -based retrieval workflows
• Implement text -to -SQL workflows with schema -aware querying and guardrails
• Build evaluation frameworks to measure retrieval relevance and response groundedness
• Monitor latency, cost, reliability, and response quality in production systems
• Manage prompt versioning, model deployments, and rollback strategies
• Design conversational UX with citations, confidence indicators, and follow -up handling
• Develop lightweight frontend applications using Flask
• Capture and utilize user feedback for continuous improvement
Required Skills:
• Strong understanding of LLMs and RAG systems
• Experience with vector databases and retrieval pipelines
• Strong proficiency in SQL and data handling
• Hands -on experience with Flask -based applications
• Knowledge of LLMOps, prompt engineering, and AI evaluation techniques
• Strong problem -solving, communication, and system design skills