Senior, ML Engineer - Unstructured Environments

Torc is hiring a Senior ML Engineer who develops our next-generation perception models for operating in complex, unstructured environments. Our systems utilize cutting-edge deep learning techniques to perceive the vehicle’s surroundings, detect objects and terrain features, and enable accurate autonomous navigation decisions in challenging conditions. 

We are seeking a highly experienced AI/ML engineer to join our team. This is an excellent opportunity to have a significant impact on autonomous systems operating in real-world, demanding environments by leveraging advanced AI techniques.

As a Senior ML Engineer, you will apply machine learning perception techniques to build an on-vehicle perception processing pipeline, using both unimodal and multimodal models to create 3D representations of terrain surfaces and navigable areas. Training, validation, data science, inference optimization, and architectural design are your daily work. You will work closely with a group of fast-moving engineers to prototype, train and deliver scientific advances in perception to vehicles operating in challenging real-world environments.

• Develop and Optimize Computer Vision Algorithms 
  • Train monocular and multimodal terrain and road surface detection models. 
  • Detect and classify objects, obstacles, traversable surfaces and environmental conditions.
  • Enhance perception systems to process multi-modal sensor data (camera, LiDAR, etc.) effectively. 
  • Utilize data science techniques to analyze model performance, data distributions, and identify corner cases. 
• Contribute to BEV and 3D Perception Architectures 
  • Design and implement deep learning models for terrain and surface inference in BEV frameworks.
  • Integrate BEV representations into navigation and motion planning pipelines. 
• Data Management and Processing 
  • Develop efficient pipelines for large-scale data processing and annotation (pseudo-labeling) of sensor data (LiDAR point clouds, image frames). 
  • Implement data augmentation, synthetic data generation, and domain adaptation strategies to improve model robustness across diverse terrain types and environmental conditions.
• Model Deployment and Optimization 
  • Deploy machine learning models on edge compute platforms, ensuring real-time performance and resource efficiency. 
  • Optimize inference pipelines for embedded and ruggedized hardware platforms.
• Cross-functional Collaboration 
  • Collaborate with robotics, software, and hardware engineers to ensure seamless integration of perception systems. 
  • Work with technical leadership to define performance metrics and improve system reliability. 
• Research and Innovation 
  • Stay current with the latest advancements in computer vision, terrain modeling, BEV models, and autonomous navigation. 
  • Translate scientific research into production-grade machine learning solutions for real
  • Publish findings in top-tier conferences and journals (optional but encouraged).
• Leadership 
  • Contribute to the model development roadmap and provide strategic advice to technical leadership. 
  • Mentor and guide junior team members to enhance their technical skills and career growth. 

• Bachelor’s degree in Computer Science, Software Engineering, or related field with 6+ years of professional applied MLE engineering experience in Autonomous Vehicle, Robotics or related industry.  
• Master’s degree in Computer Science, Software Engineering, or related field with 3+ years of professional applied ML engineering experience in autonomous systems, robotics, or a related industry. 
• Scientific understanding of machine learning for 3D BEV space modeling, including the ability to apply state-of-the-art ML research and methods in production environments. 
• Applied expertise in terrain and surface geometry modeling, multi-camera camera calibration, and sensor projection. 
• Experience analyzing data distributions and addressing long-tail edge cases. 
• Mastery of Python and PyTorch, with the ability to transition research-level code to production and deployment-ready standards 

• PhD in machine learning, computer vision, or data science.
• Proficient in writing CUDA kernels and developing custom PyTorch operations. 
• Publications at top tier computer vision / machine learning conferences or journals (CVPR, ICCV, JMLR, IJCV, NeurIPS, IROS).
• Applied experience using Ray or similar frameworks to scale ML workloads across multi-node and systems for distributed training and experimentation.
• Experience with perception systems operating in GPS-denied, GPS-challenged, or visually degraded environments.

U.S. Citizenship Requirement: This position requires access to information and systems that are restricted under U.S. law. Accordingly, only U.S. citizens are eligible for this role. This requirement is based on applicable government regulations and is not related to immigration status discrimination.

Perks of Being a Full-time Torc’r

Torc cares about our team members and we strive to provide benefits and resources to support their health, work/life balance, and future. Our culture is collaborative, energetic, and team focused. Torc offers:  

• A competitive compensation package that includes a bonus component and stock options
• 100% paid medical, dental, and vision premiums for full-time employees  
• 401K plan with a 6% employer match
• Flexibility in schedule and generous paid vacation (available immediately after start date)
• Company-wide holiday office closures
• AD+D and Life Insurance 

At Torc, we’re committed to building a diverse and inclusive workplace. We celebrate the uniqueness of our Torc’rs and do not discriminate based on race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, veteran status, or disabilities.
Even if you don’t meet 100% of the qualifications listed for this opportunity, we encourage you to apply.

US Pay Range: $199,200 - $298,800

Job ID: R-102486