Data Scientist (GenAI/LLM Applications & Agent Workflows)

Quick Facts

• Role: Data Scientist (GenAI/LLM Applications & Agent Workflows)

Description

Design and architect end-to-end GenAI/LLM-powered applications and agent workflows for complex supply chain business problems. Partner with business teams to translate opportunities into technical solutions and collaborate with data engineers to integrate LLM APIs/frameworks. Build production-quality solutions using evaluator design, monitoring, feedback loops, and iteration, including RAG pipelines and vector search with interactive visualizations.

Responsibilities

• Architect GenAI/LLM applications and agent workflows by orchestrating pre-trained foundation models
• Engage with business teams to gather requirements and convert them into technical plans
• Integrate LLM APIs and frameworks (e.g., LangChain, LangGraph) and operationalize robust solutions
• Improve deployed solutions through engineering, evals, monitoring, feedback loops, and iteration
• Present key findings to leadership in non-technical terms
• Research and evaluate emerging GenAI/agentic frameworks and advanced visualization tools
• Build RAG pipelines, vector search capabilities, and interactive dashboards/self-service tools
• Wrangle and analyze data to identify patterns, trends, and perform feature engineering
• Define and track KPIs to quantify business value of deployed AI solutions

Requirements

• PhD in relevant field with 5+ years industry experience OR MS with 8+ years hands-on industry experience
• Production-quality coding in Python and TypeScript/JavaScript plus advanced SQL; strong software engineering fundamentals
• End-to-end application development experience: backend services and RESTful APIs (e.g., FastAPI) and interactive front-ends (e.g., React/Streamlit)
• Production GenAI/LLM and ML deployment on cloud (AWS/GCP/Azure) with MLOps, model versioning, CI/CD, containerization/orchestration, and monitoring
• Hands-on LLM API integration (OpenAI/Anthropic) using LangChain/LangGraph; build agentic solutions with MCP servers, agents, and skills
• Expertise in creating evals to measure LLM output quality, accuracy, and reliability
• Background in ML libraries (Scikit-learn, TensorFlow, PyTorch) and predictive modeling (classification, regression, clustering, anomaly detection)
• Experience with forecasting, optimization, or simulation in supply chain/operations
• Ability to own projects end-to-end from scoping/prototyping through deployment and post-launch iteration

Benefits

• Opportunity to drive critical projects at the intersection of data science and GenAI-powered automation
• Work with modern LLM/agent frameworks and build production-grade, business-impacting solutions