Senior Software Engineer, ML Evaluation & Introspection Infrastructure
Core
Build and scale evaluation pipelines, embedding/vector-search systems, and model introspection infrastructure to compare self-driving model versions on large driving datasets.
Role type
Senior Software Engineer (ML Evaluation & Introspection Infrastructure)
Builds
Evaluation pipelines, embedding search systems, introspection tools, and web/CLI interfaces for engineers and AI agents.
Domain
Autonomous vehicles / Self-driving technology / ML Infrastructure
Deliverable
production ML models
Required skills
Python, SQL, large-scale batch/data pipelines, distributed compute, container orchestration (Kubernetes, AWS Batch), metrics/experimentation platforms
Preferred skills
ML evaluation infrastructure, embeddings/vector search, LLMs/VLMs/agentic workflows, autonomous vehicles/robotics, observability
Technologies
Python, SQL, Kubernetes, AWS Batch, LLMs, VLMs
Responsibilities
Build evaluation pipelines comparing model versions; own embedding and vector-search pipelines; build model introspection infrastructure; define how LLMs/VLMs change ML analysis; work with ML engineers to define measurements; build web app and CLI for engineers and agents.
