PhD Research Intern: Shape the Next‑Gen Autonomous Planner

Zendar; Berkeley (CA); On-site; USD 63,000 - 89,000; Full time

Benefits offered by this job

Hourly pay $55

Lunch provided

GPU cluster access

Mentorship

3–6 months duration

Fridge stocked

Job summary

Zendar seeks a final-year PhD student for a 40-hour/week internship in Berkeley, CA to advance learned planning and actuation for autonomous systems. You will own a research direction on the production planner and work with a team that ships it, using real fleet data to drive measurable improvements.

Ideal candidates have first-author work on motion planning or related sequential decision models, strong Python and PyTorch skills, and a collaborative mindset.

Qualifications

• Final-year PhD student (or within 12 months of defending) in computer science, electrical engineering, robotics or a related field, available for an on-site internship in Berkeley.
• First-author work in motion forecasting or planning, generative models for sequential decision making (diffusion, flow matching), reinforcement or imitation learning for control, or closed-loop simulation and evaluation.

Responsibilities

• Own one research direction on the production planner, working with researchers who ship it, on real fleet data, and present results to decision-makers.
• Test and evaluate actuation and planning pipelines: open-loop, closed-loop and on-vehicle with metrics that predict road behavior.
• Publish non-proprietary findings when appropriate.

Skills

Python

PyTorch

Education

PhD candidate

Job description

Zendar seeks a final-year PhD student for a 40-hour/week internship in Berkeley, CA to advance learned planning and actuation for autonomous systems. You will own a research direction on the production planner and work with a team that ships it, using real fleet data to drive measurable improvements.

Ideal candidates have first-author work on motion planning or related sequential decision models, strong Python and PyTorch skills, and a collaborative mindset.