ML Research Scientist, Prediction & Smart Agents

Nuro Nuro · Robotics · CA · Autonomy

Research Scientist role focused on building ML-based prediction systems for autonomous driving, involving generative sequence modeling, agent creation for simulation, and deployment on real vehicles. Requires expertise in sequential decision-making, prediction, generative modeling, and deep learning frameworks, with a preference for PhDs and publication records.

What you'd actually do

  1. Design and build scalable, machine learning-based prediction systems to generate multi-modal, realistic, and kinematically feasible trajectories.
  2. Conduct cutting-edge research in generative sequence modeling and sequential decision-making.
  3. Collaborate closely with the Planning team to design realistic and controllable agents for closed-loop simulation, enabling agent training via Reinforcement Learning (RL).
  4. Mitigate accumulated uncertainties across interconnected autonomy components.
  5. Collaborate across various autonomy teams to develop holistic solutions for top challenges, proposing ideas, prioritizing.

Skills

Required

  • Python
  • PyTorch
  • sequential decision-making
  • prediction
  • Imitation Learning
  • Deep Reinforcement Learning
  • generative modeling
  • large models (pretraining/finetuning)
  • machine learning for robotics

Nice to have

  • C++
  • Embodied AI for robotics
  • Causal reasoning
  • Model interpretability and explainability
  • Joint prediction and planning
  • Diffusion Models

What the JD emphasized

  • deploying machine learning systems onboard
  • research publications in top conferences

Other signals

  • building state-of-the-art models for predicting the behavior of surrounding traffic
  • deployed onboard as part of our planning stack
  • used offboard for realistic closed-loop simulation
  • building smart, controllable agents to enable effective closed-loop training in simulation
  • deploying machine learning systems onboard