Staff Software Engineer – Secondary Driving System

Description 

At General Motors, our Embodied AI teams are redefining what’s possible in driver assistance and automated driving, combining human‑centered design with cutting‑edge robotics, optimization, and machine learning to build systems that are both intelligent and trustworthy. 

The Secondary Driving System (SDS) is an independent perception, planning, and controls stack that keeps the vehicle operating safely for a limited time if the primary driving system becomes unavailable. SDS requests driver takeover and, when needed, executes a Minimal Risk Maneuver (MRM) to bring the vehicle to a safe stop. 

We are looking for a  Staff Software Engineer  to provide technical leadership for the  Secondary Driving System  as a whole. This is a  generalist software engineering role  focused on building robust, production‑quality C++ software across the SDS stack (perception, tracking, prediction, planning, controls, and system integration). Depth in perception, tracking, prediction, or planning is  highly preferred , but we are primarily looking for strong engineering and systems skills, with the flexibility to work where the team and product need you most.  
 

Role 

As a Staff Software Engineer on the Secondary Driving System team within Embodied AI, you will: 

• Serve as a  technical lead for SDS software  across multiple components of the stack, setting direction for algorithms, architectures, and system interfaces across features and releases. 

• Own the  end‑to‑end technical strategy  for key SDS behaviors and features, spanning perception/prediction integration, planning, controls, and system‑level interactions. 

• Balance hands‑on technical work with cross‑team leadership: you will still design and implement critical components in modern C++, while also guiding other senior and mid‑level engineers to deliver at scale. 

• Collaborate closely with experts in perception, tracking, prediction, state estimation, localization, mapping, planning, controls, systems engineering, and safety to deliver robust, fail‑operational behaviors for Super Cruise and future products.  

What you’ll be doing 

• Define technical vision & architecture  

• Set the technical direction for SDS software components with a focus on correctness, robustness, and predictable runtime behavior under tight latency and compute budgets. 

• Architect scalable, modular  multi‑sensor perception pipelines  for camera, radar, and lidar, including detection, classification, lane/road feature extraction, freespace/occupancy, and environmental context. 

• Establish and evolve  interfaces and contracts  between perception/prediction and upstream/downstream components (state estimation, localization, mapping, planning, controls, autonomy management). 

• Lead high‑impact projects  

• Lead design and delivery of  multi‑object tracking  systems (e.g., Kalman/extended/unscented filters, IMM, probabilistic data association, track lifecycle management) that provide stable, high‑quality tracks under real‑world noise and edge cases. 

• Drive development and integration of  short‑horizon motion prediction  for vehicles, VRUs, and other actors using a mix of analytical models and ML‑based forecasting, including uncertainty modeling that enables conservative, fail‑operational decisions. 

• Evaluate trade‑offs between  traditional computer vision/robotics  and  ML‑based  approaches, choosing the right tool for the problem and ensuring solutions are production‑ready under latency and compute constraints. 

• Hands‑on technical excellence  

• Design and implement critical components in  modern C++  (C++17 or later), with careful attention to memory management, concurrency, and real‑time behavior; use Python for tooling, data analysis, and ML experimentation. 

• Set and uphold high standards for software quality: clean, well‑documented APIs; rigorous code reviews; automated and regression testing; continuous integration; and rich logging and observability for on‑road incidents. 

• Profile and optimize SDS components to meet strict  runtime performance, determinism, and resource‑usage  requirements, using offline and online  evaluation frameworks and metrics  to guide iteration, regression detection, and performance tuning. 

• Cross‑functional and safety alignment  

• Work with state estimation, localization, mapping, and autonomy management partners to ensure SDS perception and prediction behavior supports reliable engagement and MRM in response to primary stack failures. 

• Partner with Safety and Systems Engineering to ensure designs and implementations align with  functional safety , redundancy, and MRM requirements for fail‑operational, eyes‑off features. 

• Represent SDS perception and prediction in  cross‑org technical forums , ensuring alignment with broader autonomy, platform, and hardware roadmaps. 

• Leadership & mentorship  

• Provide  technical mentorship  to other engineers, from onboarding to growing senior and staff‑level talent in perception/tracking/prediction and modern C++. 

• Lead and facilitate design reviews, incident post‑mortems, and cross‑team technical deep dives, raising the bar for clarity, robustness, and execution speed. 

• Help build a healthy engineering culture: pragmatic, data‑driven decision‑making; strong ownership; and a focus on safety, reliability, and customer experience.  

Qualifications 

• BS, MS, or PhD in  Computer Science, Robotics, Electrical/Mechanical Engineering , or a related field; or equivalent practical experience. 

• 8+ years  of professional software engineering experience building production systems in robotics, autonomous vehicles, or other complex real‑time/control systems, including significant experience in perception and/or prediction. 

• Strong proficiency in  modern C++  (e.g., C++14/17 or later) in large, multi‑contributor codebases; experience using  Python  for tooling, data analysis, and ML experimentation. 

• Demonstrated experience  leading technical design and delivery  of perception, tracking, or prediction systems in real‑time environments, including: 

• Multi‑sensor fusion across camera, radar, and/or lidar (e.g., object‑level fusion, occupancy/freespace fusion, early/late fusion architectures) 

• Classical computer vision and geometric algorithms (feature extraction, multi‑view geometry, stereo, SfM, SLAM/visual odometry) 

• Multi‑object tracking (Kalman/extended/unscented filters, track‑to‑track fusion, track lifecycle management) 

• Motion prediction for road users (analytical kinematic models, maneuver‑based prediction, or learned trajectory forecasting models) 

• Proven track record of delivering  reliable, high‑quality  robotics or autonomous driving software to production, including: 

• Testing strategies (simulation, HIL, scenario‑based testing, regression suites) 

• Robust metrics and dashboards for monitoring perception/prediction performance 

• Performance tuning under strict latency and compute budgets 

• Strong communication and collaboration skills, with the ability to: 

• Drive clarity in ambiguous technical spaces 

• Influence engineers and leaders across ML, systems, platform, hardware, and safety 

• Document and communicate complex technical concepts to diverse audiences 

• Passion for automated driving and robotics, and for building systems that measurably improve safety and driver experience.  

Bonus points 

• Experience building or leading  camera/radar/lidar perception and fusion  for autonomous driving or advanced driver assistance systems in production. 

• Deep expertise in  tracking and prediction  for autonomous vehicles or robotics (e.g., interaction‑aware prediction, occupancy forecasting, scene‑level prediction). 

• Hands‑on experience with  GPU/accelerator‑based ML inference , model deployment, and performance optimization (e.g., TensorRT, ONNX Runtime, custom accelerators). 

• Experience with  safety‑critical software  or working closely with functional safety teams on requirements, architectures, safety cases, and validation for fail‑operational features. 

• Background in  ROS  or similar robotics middleware, and familiarity with real‑time or embedded platforms and constraints. 

Compensation:  The compensation information is a good faith estimate only. It is based on what a successful applicant might be paid in accordance with applicable state laws. The compensation may not be representative for positions located outside of New York, Colorado, California, or Washington.  

• The salary range for this role is $218,800-$335,300. The actual base salary a successful candidate will be offered within this range will vary based on factors relevant to the position. 

• Bonus Potential: An incentive pay program offers payouts based on company performance, job level, and individual performance.

• Benefits: GM offers a variety of health and wellbeing benefit programs. Benefit options include medical, dental, vision, Health Savings Account, Flexible Spending Accounts, retirement savings plan, sickness and accident benefits, life insurance, paid vacation & holidays, tuition assistance programs, employee assistance program, GM vehicle discounts and more. 

Benefits: 

• Benefits: GM offers a variety of health and wellbeing benefit programs. Benefit options include medical, dental, vision, Health Savings Account, Flexible Spending Accounts, retirement savings plan, sickness and accident benefits, life insurance, paid vacation & holidays, tuition assistance programs, employee assistance program, GM vehicle discounts and more. 

#GM-AV-1