Senior Context Fusion AI Engineer – Autonomous Vehicles

This is a fully remote position, open to applicants in California, +2 more states.

📋 Description

• Design and create learning-driven, multimodal sensor-fusion systems that convert synchronized sensor data, ego-motion, navigation context, and driving context into a comprehensive spatiotemporal world representation.

• Construct architectures that concurrently analyze inputs from cameras, LiDAR, radar, and vehicle states while managing calibration, synchronization, coordinate transformations, sensor latency, and uncertainty.

• Develop end-to-end and multi-task models for road graph components, semantic scene comprehension, occupancy, and free-space representations, including uncertain and occluded areas.

• Create scalable multimodal fusion architectures using Transformer-based early, late, and hierarchical fusion techniques; BEV, point/voxel, and image-based representations; temporal context aggregation; and cross-modal attention.

• Establish training, fine-tuning, and evaluation pipelines for extensive multimodal datasets.

• Define multi-task objectives and metrics that balance perception quality, geometric consistency, prediction accuracy, latency, and safety-critical behaviors.

• Explore foundation-model strategies for autonomous driving, including vision-language models, multimodal pre-training, representation learning, and efficient deployment of learned world models.

• Work collaboratively with perception, mapping, prediction, planning, simulation, data, and embedded-software teams to translate research innovations into production-ready AV systems.

• Develop tools for analysis and debugging of model failures, cross-sensor discrepancies, long-tail scenarios, distribution shifts, and regressions in closed-loop simulations and on-road assessments.

⛳️ Requirements

• BS, MS, or PhD in Computer Science, Robotics, Electrical Engineering, Machine Learning, or a related technical discipline, or equivalent experience.

• Over 8 years of experience, including a minimum of 2 years in the AV or robotics sector and at least 2 years in a technical leadership role.

• Extensive experience in developing production-quality sensor-fusion, perception, state-estimation, or autonomous-driving systems.

• Proficiency in learning-based multimodal perception or fusion involving two or more cameras, LiDAR, radar, mapping, navigation, and ego-motion signals.

• Solid understanding of 3D geometry, coordinate systems, calibration, temporal synchronization, ego-motion compensation, tracking, uncertainty estimation, and sensor failure modes.

• Experience with deep learning techniques for 3D perception, scene representation, occupancy/occlusion forecasting, semantic segmentation, object detection/tracking, motion prediction, or planning.

• Strong programming skills in C++ and Python.

• Practical experience in developing, training, and optimizing deep learning models using PyTorch.

• Familiarity with Transformer, VLM, or multimodal foundation-model architectures, including pre-training, fine-tuning, distillation, quantization, or efficient inference.

• Experience in training and evaluating models at scale, encompassing distributed training, dataset curation, offline evaluation, simulation-based validation, and production monitoring.

• Capability to translate ambiguous AV challenges into quantifiable technical goals, devise solutions, and guide them to deployment.

• Experience with CUDA, distributed training, mixed-precision techniques, and efficient GPU inference utilizing NVIDIA software and hardware is highly regarded.

• Knowledge of BEV, point-cloud/voxel, neural scene representation, 3D reconstruction, occupancy-flow, or spatiotemporal world-model methodologies is a bonus.

• Publications or open-source contributions in fields such as computer vision, robotics, machine learning, 3D perception, multimodal learning, or autonomous driving are advantageous.

• Experience optimizing models for automotive-grade real-time deployment using NVIDIA GPUs, TensorRT, CUDA, or edge inference toolchains is a plus.

🏝️ Benefits

• Equity

• Benefits