About this role
As a Data Scientist – AI Engineering, you will build and optimize AI agents that support our logistics operations. You will be responsible for the end-to-end development, evaluation, and monitoring of LLM-powered agents, ensuring they are reliable, safe, and measurably improve user experiences in real-time across multiple markets.
What we are looking for 6
- Build and improve production AI agent systems, including prompts, tools, and human handover
- Develop and maintain agent evaluation suites using LLM-as-a-judge and deterministic metrics
- Implement observability and monitoring for agents, tracking quality, latency, and cost
- Ship agent changes safely with strong Python, SQL, and software engineering practices
- Analyze large datasets to define and track quality metrics, quantifying impact of changes
- Collaborate with Product, Engineering, and Operations teams to expand agent capabilities