Autonomy Engineer, Data

About the Role

We’re looking for an engineer to join our autonomy team and build the data systems that help our vehicles learn from real-world driving. Working directly with ML and vehicle software engineers, you’ll turn sensor recordings into reliable datasets for model training, evaluation, and debugging. Your work will drive the autonomy flywheel: turning driving experience into useful training data, enabling better models, and helping the team understand where to improve next. You’ll build software across data ingestion, processing, enrichment, and dataset tooling, with initial projects shaped around your strengths and interests. We welcome early-career engineers with strong software fundamentals and substantial hands-on work through internships, research, open-source contributions, or personal projects.

Key Responsibilities

• Work as part of the autonomy team to build the data workflows behind model development, evaluation, and iteration.
• Build and maintain pipelines that ingest, validate, and organize vehicle sensor recordings in our data lake.
• Develop processing workflows that enrich raw recordings with derived signals, perception labels, and road representations.
• Build tools to find, assemble, and load datasets for ML training, evaluation, and debugging.
• Run and improve backfills and reprocessing workflows as algorithms, processing steps, and dataset requirements change.
• Evolve schemas and implement migrations that keep existing data usable as the system develops.
• Investigate data quality issues, processing failures, and performance bottlenecks.
• Collaborate with autonomy teammates to understand their data needs and improve the tools that support them.

Requirements & Tech Stack

• Strong Python skills and software engineering fundamentals, including writing understandable code, testing it, and debugging unfamiliar systems.
• Hands-on technical work involving robotics, autonomous vehicles, computer vision, or other sensor-based systems. Internships, research, and substantial projects count.
• Experience building software to process and organize data, with attention to correctness and failure handling.
• An ability to break down an open-ended problem, make progress independently, and ask for help when needed.
• Curiosity about how data supports autonomy development and a willingness to work through the practical details that make a system reliable.
• Eligibility to work in the United States.

Bonus Points

• Video, multimodal sensor logs, or ML training datasets.
• Databases, schema design, data lakes, or data migrations.
• Batch processing, workflow orchestration, or cloud object storage.
• Dataset enrichment, automated labeling, or map generation.
• Data versioning, reproducible processing, or large-scale backfills.
• Working in shared codebases with code review, automated tests, and tools such as Bazel.

About Humble Robotics

We're building an autonomous, zero-emissions hauler that dramatically lowers the cost of freight with groundbreaking vision-based AI, designed for today's global logistics network. We're a fast-moving, close-knit team of AV industry veterans and innovative thinkers.

Location

• Primarily work from Humble Robotics’ San Francisco office 5 days a week.

Compensation & Benefits

• Eligible for base salary + benefits + equity compensation.
• Salary ranges are determined by role, level, and location.
• Competitive compensation and equity.
• Medical, Dental and Vision coverage for full-time employees.
• Take what you need vacation policy.
• Fully stocked kitchen with drinks, snacks and weekly catered meals.
• Collaborative in-office environment located in San Francisco.