Research Engineer, Learnable Planner (Integration) (AI)

TL;DR

Research Engineer, Learnable Planner (Integration) (AI): Integrating cutting-edge ML models into the production planning stack for autonomous trucks with an accent on simulation-based validation and end-to-end AI systems. Focus on developing interfaces for prototype testing, improving planner architecture, and ensuring high-quality code for real-world autonomy.

Location: Must be based in the US or Canada (Remote or Hybrid in Dallas, Phoenix, Pittsburgh, San Francisco, or Toronto)

Salary: $159,000 - $296,000 USD

Company

hirify.global is a technology start-up and leader in Physical AI, developing autonomous transportation systems for commercial trucks and robotaxis.

What you will do

• Integrate cutting-edge ML models into the production planning stack from development through to validation and deployment.
• Develop necessary interfaces and pipelines within the hirify.global World simulator for testing prototype and production models.
• Collaborate with motion planning sub-teams and research scientists to enhance planner architecture and novel representations.
• Maintain engineering excellence by ensuring high-quality, well-structured, and thoroughly tested code.
• Apply latest research in AI, ML, and computer vision to solve self-driving technology challenges.
• Analyze and work with large datasets from various sources and high-fidelity simulations.

Requirements

• MS/PhD in Machine Learning, Computer Science, Engineering, or a related field (exceptional Bachelor's students may be considered).
• Experience in ML-based or classical techniques for planning and decision making (e.g., RL, imitation learning, optimization, probabilistic reasoning).
• Proficiency in Python, Rust, C++, and/or CUDA.
• Experience with deep learning frameworks, specifically PyTorch.
• Solid understanding of computing fundamentals and code efficiency.
• Must be based in the United States or Canada.

Nice to have

• Experience deploying ML/DL models to a production robotics or motion planning stack.
• Experience in model evaluation, introspection, and fine-tuning.
• Strong grasp of current ML literature and state-of-the-art techniques.
• Familiarity with model compilation, TensorRT, and CUDA kernels.

Culture & Benefits

• Competitive compensation including equity awards and annual performance bonuses.
• Comprehensive medical, dental, and vision coverage for full-time employees.
• Unlimited vacation and flexible working hours with work-from-home support.
• Catered meals, snacks, and drinks provided in the office.
• Regularly scheduled team-building activities and social events, both virtual and on-site.