LLM Data Scientist

About the role

We are looking for a Large Language Model Scientist with specialized experience in Retrieval Augmented Generation (RAG) and agentic workflows built with LangGraph. You will be instrumental in developing, optimizing and deploying RAG-based LLM solutions that meet business needs.

You have a deep understanding of data science, ML, NLP and LLM fundamentals. LangGraph is central to our stack: every project uses it, so hands-on experience building stateful, multi-step agents with it is essential.

The ideal candidate also has experience with agent-based prompting techniques (e.g., LangChain), API-driven architectures for AI products, vector databases, and information retrieval pipelines that extract insights. Just as important, you listen to stakeholders, understand their business needs, and design solutions to their specific problems.

Responsibilities

• Design and develop RAG-based LLM solutions.

• Build, orchestrate and maintain agentic workflows in LangGraph across all projects, including state management, multi-step reasoning and tool use.

• Craft effective prompts that guide LLMs to produce outputs that meet business needs.

• Design, develop and refine AI products based on user and stakeholder needs and program priorities.

• Support ML Engineering teams in deploying APIs to production.

• Document Generative AI use cases.

• Develop and maintain retrieval augmented generation concepts in line with data science best practices.

• Ensure pipelines and processes run efficiently and follow company security policies and Responsible AI best practices.

Required skills

• 5+ years of experience with Python, ML and AWS cloud computing.

• 1+ years of experience in NLP and LLMs, with a strong focus on Retrieval Augmented Generation.

• Hands-on experience with LangGraph for building and orchestrating agentic, stateful LLM workflows.

• Familiarity with other agent-based LLM frameworks (e.g., LangChain).

• Familiarity with the AWS Bedrock LLM model suite and associated prompting strategies.

• Proficiency in Python for data science and AI development.

• Experience with AI training frameworks such as TensorFlow, PyTorch and Hugging Face Transformers.

• Experience with prompt engineering and fine-tuning LLMs for specific applications.

• Knowledge of vector databases and embedding techniques.

• Familiarity with DevOps practices, including CI/CD pipelines and containerization tools such as Docker and Kubernetes.

• Excellent problem-solving skills and the ability to work in a fast-paced, dynamic environment.

Preferred skills

• Experience with orchestration tools for AI product development (e.g., ArgoCD).

• Ability to create and explain data and solution flow diagrams that communicate solutions and data/AI processes to team members and internal stakeholders.

• Experience designing and deploying LLM user interfaces and frontends.