About the Role:

As a Senior Software Engineer on the Tracking Team, you will drive the delivery of both classical and machine learning solutions to core tracking challenges within our self-driving system. A central function of the tracking team is the real-time, temporally consistent estimation of the local scene (including actors, obstacles, and map features) based on a history of sensor data. In this role, you will be instrumental in the design and delivery of algorithms and models that run onboard the AV, evaluating the perception system's performance against production requirements, and contributing to the long-term technical vision of the team.

Responsibilities:

• Work in a team to deliver state-of-the-art closed- and open- world tracking systems for L4 self-driving vehicles.
• Contribute to the technical direction of the tracking team and broader perception org.
• Write robust software for real-time, resource-constrained, safety-critical applications.
• Drive highly cross-functional features and work streams from problem statement to delivery.
• Proactively identify limitations with the existing perception system and drive improvements.
• Root-cause issues that arise onboard, and provide solutions.
• Align stakeholders with strong presentation and communication skills.
• Lead challenging technical topics and build consensus.

Qualifications: 

• Experience architecting, training, and deploying ML models into real-world environments.
• Track record of driving applied research projects from start to completion, including conception, problem definition, experimentation, iteration, and finally publication or productization.
• Experience delivering perception/tracking solutions for real-time robotic applications.
• Knowledge and experience employing advanced probabilistic algorithms to solve problems involving uncertain inputs and imperfect models.
• Strong experience in software engineering and algorithm design.
• Fluency in Python and C++.

About the Role:

The Dynamic World Perception team is responsible for real-time detection of road actors and properties. This includes developing occupancy networks and other perception algorithms to accurately identify and classify all dynamic elements within the driving environment. We're looking for a Staff or Senior Engineer to lead the development, maintenance, and enhancement of our long-range detection capabilities, ensuring the required safety and performance standards are met or exceeded.

Responsibilities:

• Lead initiatives in the team to deliver state-of-the-art closed-and open-world detection capabilities.
• Contribute to expansion and fusion of existing detection models to support improving performance and extending performance at range.
• Contribute to improvement of model frameworks, architecture, and data pipelines.
• Develop robust software for onboard vehicle deployment, optimizing for real-time, resource-constrained, and safety-critical environments.
• Drive highly cross-functional features and workstreams from problem statement to delivery.
• Contribute to the technical direction of the team and broader perception org.
• Align stakeholders with strong presentation and communication skills.
• Lead challenging technical topics and build consensus.

Qualifications: 

• Extensive experience architecting, training, and deploying deep learning models into real-world environments.
• Track record of driving applied research projects from start to completion, including conception, problem definition, experimentation, iteration, and finally publication or productization.
• Experience delivering detection, segmentation, and/or tracking solutions for real-time robotic applications. Prior experience in sensor fusion is highly desirable.
• Strong experience in software engineering and machine learning algorithm design.
• Fluency in Python.
• Experience with C++.

About the Role:

As a Labeling Infrastructure Backend Engineer, you will design, build, and scale the mission-critical systems that power our data flywheel. You will be responsible for the high-performance architecture that manages massive datasets, orchestrates complex human-in-the-loop workflows, and integrates seamlessly with our machine learning pipelines. Your work ensures that our labeling operations are fast, reliable, and capable of handling the next order of magnitude in data volume.

• Architect Scalable Systems: Design and maintain robust, distributed backend services capable of managing millions of labeling tasks and high-throughput data streams with minimal latency.
• Optimize Data Pipelines: Build and refine processes to ingest raw data from diverse sources and deliver high-quality labeled outputs to model training environments.
• ML Integration: Implement "Active Learning" and "Model-in-the-loop" features, enabling automated pre-labeling and intelligent task prioritization to maximize human efficiency.
• API Development: Develop and document clean, performant APIs that serve as the bridge between our front-end labeling tools, third-party vendors, and internal ML platforms.
• Infrastructure & DevOps: Manage cloud-native infrastructure to ensure 99.9+% availability, focusing on observability, automated scaling, and cost-efficiency.
• Cross-Functional Collaboration: Partner with AI team and Product Managers to translate complex data requirements into technical specifications and durable backend solutions.

Responsibilities:

• Play a key role in designing and building the next generation of Stack’s Labeling Infrastructure.
• Implement robust architecture to track the lifecycle of every log from unlabeled to production-ready.
• Build scalable backend services for automated QA to and AI-assisted labeling plugins.
• Write high quality Python and SQL.

Qualifications: 

• Proven track record of building scalable, reliable infrastructure in a fast-paced environment.
• Ability to collaborate effectively across teams.
• Strong development experience with Python and SQL.
• Prior experience with Trino, Flyte / Airflow, and Kubernetes are a plus.
• Prior experience with ML Ops workflows is a plus.
• Prior experience building and managing data platforms for multimodal ML needs is a plus.
• Prior experience with agentic workflows is a plus. 
• Prior experience in autonomous vehicles (AV) is a plus.

About the Role:

In the ML Training, our mission is to provide a reliable, scalable, and easy to use training framework for modeling needs of Stack AV. In addition, this team is responsible for the overall developer experience of ML engineers including building tools for testing, validation, and understanding models and the data used to train them. Finally, we are responsible for model optimization and deployment.

Responsibilities: 

• Experience with both ML Platforms and building ML-based applications.
• Experience building scalable, reliable infra at a fast-paced environment working with MLEs on several different modeling teams.
• A deep understanding of design tradeoffs and ability to articulate those tradeoffs and work with others on getting alignment.
• Experience with building ML models or ML infra in the domains of autonomous vehicles, perception, and decision making (desirable but not required).
• Experience with model training, model optimization, or large data processing pipelines.

Qualifications (Preferred): 

• Built an end to end ML model pipeline including components such as logs processing, feature extraction, dataset storage, model configuration management, model training, experiment frameworks, and serving deployment.
• Shipped ML products (NLP, computer vision, recommender systems, etc.) at scale to make business impact.
• Knows how to build appropriate abstractions and tooling to ensure MLEs are able to rapidly iterate on models.
• Prior AV experience

About the Role:

The Trajectory Generation and Controls team owns the trajectory generation, optimization and controls components that power how autonomous trucks drive. You are a great fit if you have real world experience with Motion Planning, Optimization and/or Controls, as well as a proven record deploying real-time, safety critical software to production.  In this role you will work in all phases of the software development cycle, from solution design to implementation and deployment. You will collaborate with various teams in Autonomy, Systems Engineering and Operations, fostering a culture of safety, principled engineering and a customer oriented mindset.

Responsibilities:

• Own the delivery of TG&C features from design to integration, providing a well controlled, safe and comfortable vehicle experience.
• Provide input to team roadmaps and ensure timely delivery of features. 
• Work closely with systems engineers to ensure a safe, well tested product is delivered.
• Write state of the art software, using modern C++ and Python. Make extensive use of unit testing, simulation, and log simulation.
• Work closely with other Autonomy teams (Constraint Generation, Trajectory Selection, World Fusion, Prediction, ...) to design and deploy robust solutions, encompassing all aspects of autonomous driving. 
• Be involved in design and iteration exercises, and help to align stakeholders by using strong presentation and communication skills.

Qualifications: 

• BS in Computer Science, Electrical Engineering, Mechanical Engineering or closely related field. MS or PhD is a plus.
• 5+ years of software engineering experience. 
• Experience building motion planning and/or control systems for real world applications. Experience with large ground vehicles is a plus.
• Knowledge and experience with vehicle dynamics, system identification and real-time control algorithms. Experience with tooling and metrics is a plus.
• Experience with optimal control or dynamic optimization, especially in the context of model predictive control or real-time trajectory generation.
• Fluent in modern C++.
• Experience with Python.

About the Role:

Join a high-caliber team of experienced software engineers responsible for delivering some of Stack AV's most foundational technology. The team owns Clockwork, Stack's custom-built, high-performance robotics middleware powering production-grade autonomy applications — as well as StackOS, the operating system that underpins the entire vehicle software stack, and the onboard portion of Deploy Manager, which governs how software is delivered and updated on the vehicle itself. Together, these systems form the critical infrastructure backbone of Stack's safety-critical self-driving platform, operating seamlessly across the vehicle, in simulation, in the cloud, and in HIL testing environments. In this role, you will design, implement, test, and deploy new features and optimizations across this portfolio of systems to extend their capabilities, usability, performance, and reliability.

Responsibilities:

• Design, implement, and maintain StackOS, Stack AV's vehicle operating system, ensuring it meets the reliability and performance demands of a safety-critical autonomy platform.
• Drive the architecture and implementation of the onboard portion of Deploy Manager, ensuring safe, reliable, and efficient software delivery to the vehicle.
• Proactively work with internal customers to design & implement new features from ideation to deployment. 
• Automate processes related to assembling new self-driving vehicles from-scratch, and updating their software on an ongoing basis.
• Continually identify opportunities for improving the performance, reliability, and usability of StackOS and Deploy, evaluating tradeoffs amongst multiple options.
• Partner with safety and validation teams to ensure StackOS and Deploy Manager meet functional safety requirements.
• Ensure delivery of high quality software through the principled and consistent use of best practices including robust automated testing, manual and automated code review.

Qualifications: 

• Strong C++ development experience is required, some Python experience highly preferred
• Expert knowledge of software engineering and algorithm design principles
• Significant experience developing high performance software systems, deployed in resource constrained environments, preferably for safety critical applications
• Expert level understanding of Linux and building Linux distributions via Yocto
• Strong understanding of the POSIX programming environment, Linux, and concurrent programming
• Strong understanding of Networking fundamentals
• Comfortable working with & debugging embedded systems
• Experience working with common tooling such as Bazel, Boost, etc
• Excellent communication skills and ability to work in a team environment
• Domain experience working in autonomous driving, robotics or related industry is highly desired
• Experience with the Nvidia ecosystem and DriveOS, QNX

About the Role:

The Perception Architecture team is responsible for tackling complex, cross-cutting issues in Stack AV’s approach to perception development and accelerating our delivery of perception capabilities. Many problems in the self-driving trucking industry are not well represented in the literature, requiring novel approaches or formulations to tackle challenging perception problems for the product.

As a Staff Software Engineer, you will drive the development of foundational ML architecture and systematic approaches to challenging, cross-cutting perception problems to ensure the self-driving system scales robustly and efficiently. This role will work closely with other teams to identify pain points and forward looking challenges, develop novel experiments to define future direction, and collaborate with other AI teams to convert these discoveries into product.

Responsibilities:

• Contribute to the technical direction of the Perception Architecture team and the broader perception organization.
• Design and develop core machine learning components and architectures that enable the perception system to scale and reliably address complex, long-tail driving scenarios.
• Drive the initial implementation and prototyping of key architectural decisions, such as handling long tail challenges or long range detection.
• Contribute to the improvement of model frameworks, architecture, and data pipelines to eliminate development bottlenecks and accelerate model iteration.
• Lead challenging technical topics and build consensus across sister teams (e.g., dynamic world, static world) and stakeholders to ensure autonomy-wide alignment.

Qualifications:

• BS (with 6+ years of experience), MS (with 5+ years of experience), or PhD (with 3+ years of experience) in a perception-related field, such as Robotics, Computer Vision, or Machine Learning.
• Extensive experience architecting, training, and deploying deep learning models into real-world, safety-critical environments.
• Track record of driving applied research or engineering projects from conception and experimentation to successful productization.
• Strong experience in software engineering, machine learning algorithm design, and building data/metrics pipelines for ML development.
• Fluency in Python and hands-on experience with C++.
• Experience delivering detection, segmentation, tracking, or other perception solutions for real-time robotic applications, with prior experience in sensor fusion being highly desirable.

About the Role:

The AI Data Infrastructure team sits between Stack’s data and its engineers. We provide tooling and infrastructure to process petabytes of data per month into actionable insights for ML and autonomy engineers. In particular, we provide data pipelines to run tasks on new data, services and frontend to search for data, and tooling to stream and transform data in our various data storage mediums.

• Data Processing: we are building state of the art infrastructure to support our scaling fleet and ML engineering needs. For this role, you would be responsible for ensuring our processing pipelines are customer friendly, fault tolerant and performant. 
• Data Search: we provide our end users with a platform that combines searching across our metadata stores, vector database, and parts of our data warehouse and then visualize the data (think YouTube). You would be coming in and working with ML and autonomy stakeholders to improve the reliability of the pipelines that feed into our search platform.  
• Data Lineage: we are getting started with building our data lineage system that will track the usage of all data at Stack. You would work with our stakeholders to ensure our system is widely adopted and address customer pain points.

Responsibilities:

• Play a key role in designing and building the next generation of data infrastructure.
• Build low latency/high throughput, fault tolerant  batch or stream processing systems.
• Build scalable backend services for data search and data curation systems.
• Write high quality Python and SQL.

Qualifications: 

• Proven track record of building scalable, reliable infrastructure in a fast-paced environment.
• Ability to collaborate effectively across teams.
• Strong development experience with Python and SQL.
• Prior experience with Apache Iceberg, Trino, SQLMesh, Flyte / Airflow, and Kubernetes are a plus.
• Prior experience building and managing data platforms for multimodal ML needs is a plus.
• Prior experience with agentic workflows is a plus.
• Prior experience in autonomous vehicles (AV) is a plus.

#LI-AW1

About the Role:

In the ML Data Understanding team, our mission is to provide trusted and useful data to efficiently power all of Stack's ML applications end-to-end from mining to training to safety evaluation. We work hand in hand with AV autonomy teams to provide cutting edge solutions to all their data needs, working across data engineering, mining, modeling and infrastructure. In particular, we provide services to find (data mining), curate (datasets), annotate (data labeling), search and serve (high throughput data access) data for all ML needs.

• Data Mining: We are building a framework and infrastructure to find interesting events quickly and flexibly. As part of this mission, you would be setting the direction for and helping us build an inference service using LLMs, open-world models and vector databases.
• Semantic Search for Data Mining: We are building the infrastructure of a highly scalable semantic search service for multimodal data to find interesting events quickly and flexibly. As part of this mission, you would be setting the direction for and helping us build an inference service using the latest AI models & approaches. 
• Dataset management for training: We are building state of the art infrastructure to support machine learning training and inference workloads using OSS components such as Ray, Spark, Lance and Iceberg.

Responsibilities:

• Build state-of-art multimodal data mining and semantic search solutions to power AV product development.
• Develop data understanding platform infrastructure for real-time querying/vector databases and batch/stream processing using technologies like Ray, Spark, Lance, or similar.
• Deliver end-to-end data mining solutions that span onboard (C++) and offboard (ML & Data Infra) infrastructure to accelerate AV product development. 
• Develop e2e solution for real-time semantic search services (text/images/videos) and vector DBs.
• Discover and identify key issues in existing ML infra and proactively improve system performance.
• Build low latency/high throughput batch or stream processing pipelines.
• Drive technical discussions across multiple orgs and deliver solutions on a timely basis.
• Architect and tune ETL pipelines to maximize GPU/CPU/Ram utilization.
• Write readable and high-performance Python/C++ code.

Qualifications: 

• Experience with both ML platforms and building ML-based applications (modeling experience is a bonus).
• Proven track record of building scalable, reliable infrastructure in a fast-paced environment.
• Ability to collaborate effectively across teams.
• Experience building or using ML infrastructure for a large number of customer teams.
• Deep understanding of design trade-offs with the ability to articulate those trade-offs and achieve alignment with others.
• Experience in building ML models or infrastructure in domains such as autonomous vehicles, perception, and decision-making (desirable but not required).
• Experience with model training, model optimization, or large data processing pipelines.
• Prior experience in autonomous vehicles (AV) is a plus.
• 6+ years of experience with:
  • Multimodal data indexing and inference pipelines.
  • Building semantic search service, embedding generation for video/images and vector DB.
  • Large scale ML pipelines (Airflow/Flyte) and model optimization.

About the Role:

The ML Training Acceleration team is dedicated to increasing Stack AV's product development velocity by accelerating machine learning iterations. Our core mission is to deliver a training system that is reliable, scalable, user-friendly and observable. This involves profiling, optimizing, and fine-tuning our ML models, as well as evangelizing best practices and frameworks among Machine Learning Engineers (MLEs) across the company.

Responsibilities: 

• Analyze ML models to identify and resolve performance bottlenecks.
• Incorporate OSS tools to enable ML engineers self-sufficiently profile and optimize models.
• Deliver solutions to streamline model deployment across various hardware platforms.
• Collaborate with ML researchers to balance model accuracy and speed.
• Implement optimizations using CUDA, Triton, and custom kernels.
• Promote Engineering Excellence: Maintain a high bar for engineering excellence in their own work but also set a culture of engineering excellence within the team.

Qualifications: 

• Education: Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field
• Experience: 5+ years of experience (including experience with GPU programming and optimization)
• Technical Skills:
  • Strong programming skills in C++ and Python
  • Proven experience in GPU programming and optimization
  • Familiarity with deep learning frameworks, especially PyTorch
  • CUDA programming
  • Triton language for GPU kernels
  • PyTorch optimization techniques
  • TensorRT implementation
  • ONNX model conversion and deployment
  • Custom GPU kernel development
  • Deep understanding of GPU architectures and performance optimization
• Problem-Solving: Strong analytical and problem-solving skills
• Communication: Excellent verbal and written communication skills, with the ability to convey complex technical concepts to non-technical stakeholders
• Autonomous vehicles (AV) experience is a bonus