Sr. Data Scientist/ Lead Data Scientist

Contract role - Sr. Data Scientist to Lead level

Required experience

Hands-on experience with LLMs, including prompt engineering, fine-tuning, or agentic

architectures (LangGraph, AutoGen, CrewAI, etc.).

Strong programming skills in Python, with experience in building scalable ML/AI applications.

Model evaluation expertise for LLM-based systems, including designing metrics and running A/B

tests or offline experiments.

Python

LangChain / LangGraph / CrewAI / AutoGen (any relevant)

Hugging Face Transformers

Vector DBs (e.g., FAISS, Weaviate, Pinecone)

Git, VS Code, and cloud platforms (Google Cloud Platform preferred)

Contribute to the development of a Knowledge Assistant for the Pro & Services organization, with a

focus on natural language understanding and agentic workflows.

Build, evaluate, and iterate on LLM-powered agents to support task execution, reasoning, and

retrieval across structured and unstructured data.

Collaborate closely with product managers, engineers, and other data scientists to integrate

intelligent systems into customer and associate-facing platforms.

Own model evaluation and validation pipelines, especially for LLM and RAG workflows, including

performance tracking and ablation studies.

Write clean, production-grade Python code and contribute to reusable components and pipelines.

Apply critical thinking and analytical problem-solving to identify patterns, define rules, and

optimize agent behaviors.

Preferred experience

Experience with retrieval-augmented generation (RAG) and knowledge graphs, vector Databases.

Retail or digital experience

Designing custom evaluation pipelines for hallucination detection, factual consistency, and user

relevance.

Familiarity with frameworks like TruLens, Ragas, Promptfoo, or ReAct-style evaluation loops.

Implementing guardrails to ensure safety, compliance, or brand alignment in LLM outputs.

Prior exposure to PhD-level research or applied LLM work in industry or academia.

Disqualifiers

Generic ML experience without any LLM, agentic, or applied AI work.

Heavy reliance on low-code/no-code ML platforms without demonstrated software engineering capability.

Lack of hands-on involvement in end-to-end model deployment or evaluation.

Team environment

The candidate will join a tight-knit, cross-functional AI team focused on building LLM-powered

capabilities for Pro and Services use cases. The team includes Data Scientists, AI Engineers and a

AI Product Manager

The environment is collaborative and fast-paced, with strong product orientation, a culture of rapid

experimentation, and close alignment with business stakeholders. Candidates should be comfortable with

ambiguity, quick pivots, and high-impact deliverables.

Any Additional Details:

Ideal for someone passionate about pushing the boundaries of LLM applications in real-world settings.

There's significant opportunity to shape foundational tools that will power experiences for Pro

customers and store associates.