ML Research Scientist, Prediction & Smart Agents
Build state-of-the-art ML models to predict traffic behavior for autonomous driving, using generative sequence modeling and controllable agents for planning and simulation. Requires PhD preferred, 2+ years deploying ML systems, and expertise in PyTorch and robotics ML.
About the job
About the Work
- Design and build scalable, machine learning-based prediction systems to generate multi-modal, realistic, and kinematically feasible trajectories.
- Conduct cutting-edge research in generative sequence modeling and sequential decision-making, including:
- Scalable generative sequence modeling approaches.
- Marginal, conditional, and joint distribution modeling for interactive agents.
- Transformer-based encoder-decoder architectures.
- Large generative models and diffusion models.
- Controllability of agents via conditioning, guidance, and other techniques.
- Collaborate closely with the Planning team to design realistic and controllable agents for closed-loop simulation, enabling agent training via Reinforcement Learning (RL).
- Mitigate accumulated uncertainties across interconnected autonomy components.
- Collaborate across various autonomy teams to develop holistic solutions for top challenges, proposing ideas, prioritizing.
- Derive practical, deployable solutions and see them deployed on real-world vehicles.
About You
- Education: M.Sc. or Ph.D. (preferable) in Computer Science, Artificial Intelligence, Mathematics, or related field.
- Expertise: Research experience in sequential decision-making, prediction, Imitation Learning, Deep Reinforcement Learning, generative modeling, large models, or ML for robotics.
- Technical Skills: Strong problem solving and programming in Python (required), C++ (beneficial), and ML frameworks like PyTorch.
- Experience: 2+ years deploying ML systems onboard, ideally in prediction.
- Publications: Demonstrated research in top conferences (NeurIPS, ICLR, ICML, CVPR, RSS, CoRL, ICRA, IROS).
Nice to have: Deep background in Embodied AI for robotics, Causal reasoning, Model interpretability, Joint prediction and planning, Diffusion Models.
Compensation: Base pay range $193,930 - $291,150, plus annual performance bonus, equity, and benefits.
Skills
PyTorch, Python, C++, Transformer, Generative Models, Diffusion Models, Reinforcement Learning, Imitation Learning, Sequential Decision-Making, Machine Learning
Similar jobs
AI Research jobs
Fireworks AI
San Mateo, CAConduct foundational research on LLMs and multimodal systems, designing architectures and training methods and helping move prototypes into production. The role targets PhD researchers graduating by December 2026 with strong machine-learning research and programming experience.
Perplexity
San Francisco, CABuild and evolve the agent harness powering Perplexity’s flagship answer experience, improving orchestration, context management, performance, reliability, observability, and evaluation. The role requires strong software engineering skills, Python proficiency, and experience shipping large-scale AI systems.
Applied Intuition
Sunnyvale, CA
Research Engineer developing and deploying machine-learning algorithms for autonomous driving and robotics systems. The role targets recent MS or PhD graduates with experience in areas such as foundation models, diffusion policies, reinforcement learning, computer vision, and robotics.
OpenAI
San Francisco, CA
Researcher developing and publishing mechanistic interpretability techniques, building infrastructure to study model internals, and guiding alignment-focused research. Requires research experience in machine learning or a related field, strong engineering skills, and proficiency in Python or similar languages.
GrayMatter Robotics
Los Angeles, CA
Conduct research and develop foundation models for robotic manipulation and high-precision manufacturing, taking projects from data curation through deployment on industrial robots. The role requires current PhD study, strong Python and deep learning expertise, robotics simulation experience, and research in foundation models.