About
Remote Total Years of experience 10-12 years. 6 months+ Occasional travel to the client location is required. Candidates might need to overlap with offshore on need basis. Must have skills: Elastic Search, Generative AI Fundamentals (Strong), Python for Data Science (Strong), RAG Good to have skills: Data Scientist with ~6+ years of expertise in Natural Language Processing (NLP), Large Language Models (LLMs), and Generative AI (GenAI). The ideal candidate will have hands-on experience with search-related work, including relevance tuning, text classification, and topic modeling. Additionally, experience in building Retrieval-Augmented Generation (RAG) pipelines for search and chat applications is highly desired. Key Responsibilities: Develop and optimize NLP models for text classification, text clustering, topic modeling, and relevance tuning in search. Work with LLMs to build advanced generative AI solutions for search and chat applications. Design and implement Retrieval-Augmented Generation (RAG) pipelines to improve search and conversational AI systems. Collaborate with cross-functional teams to deploy data-driven search enhancements and GenAI solutions. Analyze and fine-tune search relevance based on user behavior and search intent from querylog. Experience in running and fine-tuning models from Hugging face Familiarity with building and deploying RAG pipelines Familiarity with vector databases like Elasticsearch, Pinecone, etc. Strong programming skills (e.g., Python, TensorFlow, PyTorch, SQL) Experience in model deployment & MLOps is a plus Experience with cloud platforms (AWS) is a plus. Let me know if you have any questions.
Languages
- English
Notice for Users
This job comes from a TieTalent partner platform. Click "Apply Now" to submit your application directly on their site.