You will:- Designing and Building Machine Learning Models: Writing clean, high-performance code to implement core algorithms for entity-centric lane geometry detection and relational topology decoding (e.g., merges, splits, predecessor/successor connectivity).
- Running Experiments and Training Pipelines: Setting up data pipelines and training neural networks across vehicle sensor modalities and map priors, leveraging techniques like proxy auto-encoding and prior-dropout to handle real-world challenges like construction zones and occlusions.
- Benchmarking and Analyzing Performance: Creating structured evaluation metrics to benchmark model accuracy and topological correctness across complex intersections, analyzing failure cases, and iterating on architectural designs.
- Cross-Functional Collaboration: Partnering closely with research mentors, buddy, and upstream/downstream engineering teams to evaluate downstream planning impact and package insights for publication or internal deployment.
You have:- Currently pursuing a Master's or PhD in Computer Science, Robotics, Electrical Engineering, Machine Learning, or a related quantitative discipline.
- Strong programming proficiency in Python and solid experience with modern deep learning frameworks (e.g., PyTorch, JAX, or TensorFlow).
- Hands-on experience designing, training, and debugging deep learning architectures for Computer Vision, 3D Perception, or Graph Neural Networks (e.g., Transformers, DETR-based detectors, GNNs, or BEV perception).
- Solid foundational knowledge of 2D/3D geometry, coordinate transformations, and spatial/relational reasoning.
We prefer:- Track record of publications in top-tier conferences in machine learning, computer vision, or robotics (e.g., CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, ICRA, CoRL, AAAI).
- Experience with vectorized HD map learning, lane topology estimation, or dynamic roadgraph modeling (e.g., MapTR, TopoNet, LaneGAP, or similar architectures).
- Experience with large-scale distributed model training and data infrastructure (e.g., TPU/GPU clusters, Ray, Jax/Flax, or multi-GPU pipelines).
- Familiarity with autonomous vehicle perception stacks, sensor fusion (camera, LiDAR), and downstream motion planning constraints.
Note: This will be a hybrid onsite internship position. We will accept resumes on a rolling basis until the role is filled. To be in consideration for multiple roles, you will need to apply to each one individually - please apply to the top 3 roles you are interested in.
The expected hourly rate for this full-time position is listed below. Interns are also eligible to participate in the Company's generous benefits programs, subject to eligibility requirements.
Hourly Masters Pay
$70-$70 USD
The expected hourly rate for this full-time position is listed below. Interns are also eligible to participate in the Company's generous benefits programs, subject to eligibility requirements.
Hourly PhD Pay
$85-$85 USD
