Behavior & Planning (ML Research) Intern (Autonomous Driving)

Location: Mountain View, San Francisco, or Pittsburgh, United States; remote workplace type with in-person office attendance expected at least 3 days per week, and up to 5 days based on operational needs.

Salary: $47–$65 per hour depending on location and degree level. Mountain View or San Francisco: $52/hour bachelor's, $58/hour master's, $65/hour doctoral. Pittsburgh: $47/hour bachelor's, $52/hour master's, $58/hour doctoral.

Company

hirify.global develops self-driving technology for mobility and logistics, including the hirify.global Driver.

What you will do

• Develop end-to-end planning or prediction models for the hirify.global Driver using imitation learning, reinforcement learning, and/or classical motion planning.
• Formulate ambiguous driving-behavior problems as concrete machine-learning or optimization problems.
• Design and evaluate models while reasoning about competing objectives such as progress versus safety and about uncertainty.
• Work with autonomy- and robotics-scale datasets and benchmarks.
• Present project plans and regular progress updates while working closely with a mentor.

Requirements

• Currently pursuing a bachelor's, master's, or doctoral degree in Computer Science, Robotics, or a related field, with a research or machine-learning focus.
• Strong machine-learning foundations and hands-on PyTorch experience, including custom dataloaders, architectures, and loss functions.
• Some exposure to imitation learning, reinforcement learning, or motion planning.
• Experience training models on large-scale, non-toy datasets or benchmarks.
• Ability to reason mathematically about optimization objectives.
• Awareness of the compounding-error and distribution-shift problem in imitation learning.

Nice to have

• Publication record at a peer-reviewed venue.
• Experience with constrained optimization or preference tuning, such as RLHF or DPO.
• Experience with online reinforcement learning or interactive learning, such as DAgger.

Culture & Benefits

• In-person collaboration is emphasized, with office attendance expected at least 3 days per week and up to 5 days depending on operational needs.
• Work is conducted with a strong emphasis on safety, integrity, collaboration, and inclusion.
• Reasonable accommodations are available for qualified applicants with disabilities and disabled veterans.