Autonomy Metrics Engineer — Data Pipelines & Evaluation

applied; Sunnyvale (CA); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Equity

Health insurance

401k retirement benefits

Wellness stipend

Paid time off

Learning stipend

Job summary

Applied Intuition, Inc. is seeking a SDS Evaluation engineer to define and own metrics measuring autonomy stack performance. You will build datasets (real and synthetic) to evaluate perception, prediction, and planning, and turn questions into measurable signals for developers and leadership.

You will collaborate with stack developers to improve evaluation infrastructure, ensure fast runs, reliability, and clear result interpretation, while mentoring junior engineers.

Qualifications

• Master’s, PhD, or equivalent work experience in Engineering such as Computer Science, Electrical Engineering, Software Engineering
• 3–5 years of experience in software or data infrastructure engineering
• Expertise in building and scaling data pipelines, distributed systems, or ML infrastructure.

Responsibilities

• Define and own metrics for one or more autonomy behavior areas, from requirements through implementation
• Build and curate datasets — real and synthetic — that those metrics run against
• Design visualizations and reporting that make progressions and regressions obvious at a glance
• Partner with perception, prediction, and planning teams to turn their open questions into measurable signals
• Improve evaluation infrastructure: trigger paths, run time, reliability, and result presentation
• Mentor junior engineers and contribute to best practices for data-centric development

Skills

Python

Data pipelines

Spark

Airflow

Kafka

ML infrastructure

Distributed systems

Data-driven development

Education

Master’s/PhD in Engineering or Computer Science

Tools

Python

Job description

Applied Intuition, Inc. is seeking a SDS Evaluation engineer to define and own metrics measuring autonomy stack performance. You will build datasets (real and synthetic) to evaluate perception, prediction, and planning, and turn questions into measurable signals for developers and leadership.

You will collaborate with stack developers to improve evaluation infrastructure, ensure fast runs, reliability, and clear result interpretation, while mentoring junior engineers.