Staff Software Engineer, Learned & Hybrid Behavior Planning
Kodiak AI is an active public company providing AI-powered autonomous ground-vehicle technology, principally through the Kodiak Driver for commercial trucking, industrial trucking, and defense applications.
Funding history
About Kodiak AI, Inc.
Kodiak Driver combines AI-powered software and modular, vehicle-agnostic hardware to enable driverless vehicle operations. Kodiak commercializes the technology through a Driver-as-a-Service model and serves trucking, industrial, and defense customers.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will integrate learned models into the behavior-planning stack and work with machine-learning partners on model requirements, evaluation, and deployment. You will design hybrid planning strategies, define validation and safety criteria, analyze model behavior, lead technical designs, and mentor engineers.
Requirements
- Experience in autonomous vehicles, robotics, or a related autonomy domain
- Technical background in behavior planning, decision-making, or motion planning
- C++ proficiency
- Experience with heuristic or classical planning systems
- Experience integrating or developing learned behavior policies, behavior classification, trajectory prediction, or actor-intent models
- Ability to reason about safety, system behavior, evaluation, and deployment risk
- Cross-functional communication and technical leadership
Responsibilities
- Lead planning-side integration of learned models into behavior planning
- Collaborate on model improvements, requirements, evaluation, and deployment
- Develop learned planning components and ML-driven planning signals
- Design strategies that balance learned components with heuristic planning systems
- Define validation, fallback, monitoring, and safety criteria
- Debug and analyze model behavior using simulation, logs, metrics, and autonomy data
- Lead technical designs and mentor engineers