Machine Learning Engineer (Behavior and Planning)
Posted Updated
- We are looking for a Machine Learning Engineer with expertise in ML-first behavior prediction and planning
- You will develop ML-first behavior modules that can predict the future trajectories and behaviors of road users and predict their interactions
- You will work closely with the perception team on areas such as training data generation, and with the planning team on ML-based planner development
- You will also have the opportunity to collaborate with our research teams on state-of-the-art architectures and techniques. Your work will have a tangible impact, deployed across diverse domains including passenger vehicles, trucking, and mining
- In addition to your engineering contributions, by working in our dynamic and customer-focused team culture, you will contribute to and learn from best practices in the nascent autonomy industry
- Prototype, evaluate, refine, and deploy state-of-the-art ML algorithms that generate driving trajectories for autonomous vehicles and other road users in the scene
- Leverage established products at Applied Intuition to build the software and infra foundation for behavior-specific ML development
- Collaborate with perception and planning engineers as well as research teams on cross-team state-of-the-art models and techniques
- Experience with the end-to-end development cycle of deep learning models
- 2+ years of experience building production software using modern software practices
- Expertise in at least one of the following subdomains: modeling, input pipelines, evaluation, deployment, or model optimization
- Fluency in Python with intermediate experience in C++
- Bachelor’s in Computer Science, Electrical Engineering, Robotics, or related field
- Don’t meet every single requirement? If you’re excited about this role but your past experience doesn’t align perfectly with every qualification in the job description, we encourage you to apply anyway. You may be just the right candidate for this or other roles
- Experience with driver assistance or autonomous driving systems
- Peer-reviewed research at machine learning conferences like NeurIPS, CVPR, ICML, ICLR, ICCV, ECCV, IROS, or ICRA
- Experience in evaluating and improving system-in-the-loop model performance