Senior AI Engineer — Inference & Agent Systems

Onsite United States

pythondockergokafka engineering

greenhouse

Match & cover letter

Create a profile to see your match and get a cover letter for this role.

Create profile and match

Job description

You will optimize AI agent systems for speed and reliability in the United States. This role involves designing complex pipelines and evaluation frameworks for production-level AI applications.

Details

United States, work from office
Experience with production-level systems
Skills: Python, Go, Docker, Kafka

The work

Drive time-to-first-token (TTFT) below 400ms for agent pipelines
Design Plan-Execute-Synthesize pipelines for parallel execution
Own the evaluation framework and regression detection
Optimize model serving and cold start processes