Description

Develop NLP models and generative AI solutions to enhance search and conversational systems.

You will own the full lifecycle of GenAI projects, from model fine-tuning to RAG pipeline implementation and search relevance optimization.

Responsibilities

• Develop and optimize NLP models for text classification, clustering, topic modeling, and relevance tuning.
• Build generative AI solutions using LLMs for search and chat applications.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines.
• Analyze and fine-tune search relevance using user behavior and querylog data.
• Collaborate with cross-functional teams to deploy GenAI solutions and search enhancements.

Required Skills

• 6+ years of experience in Natural Language Processing (NLP), LLMs, and Generative AI (GenAI).
• Hands-on experience with search-related work including relevance tuning and text classification.
• Experience running and fine-tuning models from Hugging Face.
• Proficiency in Python, TensorFlow, PyTorch, and SQL.
• Familiarity with building and deploying RAG pipelines.
• Familiarity with vector databases such as Elasticsearch or Pinecone.
• Bachelor's degree in Computer Science.

Preferred Skills

• Experience with model deployment and MLOps.
• Experience with AWS cloud platforms.

Key Skills

Education

Bachelor's degree in Computer Science