About the team:
Materra is on a mission to radically reduce global waste and move to a true circular economy. The team has developed technology that identifies waste material at the molecular level—starting with plastics. Materra works with industry partners to improve the way recycling centers process plastics using AI and robotics, to make recycling more affordable and scalable.
About the Role:
We are looking for a Software Engineer, Edge Systems & Runtime to join our team, focusing on high-performance C++ software and on-device machine learning execution. In this role, you will work on low-latency software pipelines that process multi-sensor data streams and execute deep learning models on edge GPUs.
Your primary focus will be optimizing our production C++ runtime infrastructure, refining memory usage, improving data streaming between host and device, and tuning execution engines to squeeze out low-latency optimizations within single-digit milliseconds.
Key Responsibilities
- Profile and optimize established C++ software pipelines and GPU runtime engines to reduce latency and maximize hardware utilization.
- Refine host-to-device streaming pipelines using efficient memory management patterns (e.g., pinned memory, zero-copy buffers, lock-free queues).
- Deploy, update, and optimize deep learning model execution runtimes (e.g., TensorRT, CUDA, ONNX Runtime) on edge GPUs.
- Enhance asynchronous C++ data streams routing multi-sensor inputs into model inference loops.
- Collaborate with machine learning engineers to ensure smooth handoffs from training pipelines to production C++ runtimes.
Requirements
- Education: Degree in Computer Science, Computer Engineering, Electrical Engineering, Robotics, or a related technical field.
- Modern C++ Proficiency: 3+ years expertise in modern C++ (C++17/20), including multithreading, asynchronous I/O, IPC, and manual/smart memory management.
- On-Device ML Deployment: 3+ years hands-on experience profiling, compiling, and optimizing deep learning models for edge hardware using TensorRT, CUDA, ONNX, or similar acceleration frameworks.
- Systems Optimization: Proven experience navigating, profiling, and optimizing C++ execution paths under strict, low-latency performance constraints.
Preferred Skills
- Sensor & Hardware Integration: Familiarity with hardware communication APIs, SDKs, or sensor streams (e.g., GigE Vision, GenICam, frame-grabbers, or point clouds).
- Domain Experience: 3+ years exposure to real-time perception systems in robotics, industrial automation, autonomous vehicles, or video processing engines.
- Scripting & Automation: Proficiency in Python for rapid prototyping and system integration.
- Advanced Acceleration: Experience writing custom CUDA kernels, custom TensorRT plugins, or working with real-time OS extensions.
The US base salary range for this full-time position is $166,000 - $244,000 + bonus + equity + benefits. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your location during the hiring process.
Please note that the compensation details listed in US role postings reflect the base salary only, and do not include bonus, equity, or benefits.
