Looking For Senior Data Scientist - Generative & Agentic AI -Remote

Location : Remote

Exp- 5 to 10 Years

LLMs, Agentic AI, Langchain, Langgraph/crew AI/ AutoGen,(Retrieval Augmented Generation) RAG, Reranker, Embedding Models, Hugging Face, OpenAI, Claude, Anthropic, Gemini, NLP, BERT, Transformers, Fine Tuning, Zeroshot/Few Short prompting

Key Responsibilities:

• Design, develop, and iterate on LLM-powered agents and multi-agent AI systems using frameworks like LangGraph, LangChain, and AutoGen.
• Build advanced Retrieval-Augmented Generation (RAG) pipelines to deliver context-aware, grounded AI responses.
• Integrate Generative AI solutions into our product ecosystem via robust FastAPI services and Azure AI pipelines.
• Develop and maintain agent orchestration flows, including tools for memory, planning, and tool-use capabilities.
• Collaborate cross-functionally with product, engineering, and domain experts to identify opportunities for autonomous AI workflows in legal and regulatory tasks.
• Apply advanced Natural Language Processing (NLP) techniques to unstructured legal data to extract insights and drive product capabilities.
• Maintain and optimize databases and document stores (e.g., Solr, PostgreSQL, Azure CosmosDB) for LLM data pipelines.
• Stay current with the latest in GenAI, autonomous agent frameworks, vector databases, and prompt engineering strategies.

Required Skills & Experience:

• Proficiency in Python, including libraries such as LangChain, LangGraph, Transformers, spaCy, and scikit-learn.
• Deep hands-on experience with Large Language Models (LLMs) (e.g., GPT, Claude, LLaMA) and fine-tuning techniques.
• Experience with agentic AI frameworks and building tool-using agents that reason and act autonomously.
• Strong knowledge of FastAPI for deploying AI services and MLflow for model management.
• Experience with cloud-native AI workflows using Azure AI, OpenAI APIs, or AWS Bedrock.
• Familiarity with RAG pipelines, vector embeddings, and semantic search for grounded AI output.
• Comfortable with Linux, shell scripting, and working in distributed, containerized environments.
• Solid understanding of statistical modeling, data structures, algorithms, and database design.
• Proficiency with SQL, experience with Solr via Python, and exposure to vector stores.
• Strong problem-solving skills, a self-motivated mindset, and the ability to work effectively across distributed teams.

Preferred Qualifications:

• Bachelors degree in computer science, Engineering, Statistics, Mathematics, or a related field; a Masters degree is a plus.
• 5+ years of experience supporting software products or applications in the AI/ML domain.
• Experience developing autonomous AI agents for enterprise applications.

Interested candidate can apply to sathya@clarityconsulting.in