Redwood Materials
Software Engineer - ML/Computer Vision (Battery Sorting)
$152K–$200K
McCarran, NV +2 · Full-time · Posted Jun 23, 2026
- Location
- McCarran, NV
San Francisco, California, United States
San Francisco, California, United States - Experience
- 2+ years of industry experience working with machine learning models, preferably in computer vision.
- Education
- B.S. in Computer Science, Electrical Engineering, or a related field, or equivalent practical experience.
About the job
Build and operate production software and computer vision systems that classify and route end-of-life batteries in automated factory sorting.
What you'll do
- Develop and maintain production sorting software, including ML inference, image acquisition, sensor integration, and hardware-adjacent controls.
- Train and deploy computer vision models, monitor their production performance, and improve them through analysis and retraining.
- Build services connecting ML outputs to MES, HMI, and PLC/controls interfaces, and support observability and deployment workflows.
What they ask for
- 2+ years of industry experience working with machine learning models, preferably in computer vision.
- Hands-on experience with ML frameworks and libraries such as PyTorch and OpenCV.
- Experience contributing to production codebases and pipelines, emphasizing clean, documented, and tested code.
- B.S. in Computer Science, Electrical Engineering, or a related field, or equivalent practical experience.
Nice to have
- Experience with ML experiment tools such as MLflow, or edge deployment/model optimization techniques such as quantization, TensorRT, or ONNX Runtime.
- Experience with OCR, image classification, multi-sensor or multimodal fusion, or industrial/manufacturing environments.
Pay
$152,500 — $200,000 USD (base salary)
Tools
PyTorch, OpenCV, MLflow, TensorRT, ONNX Runtime, MES, HMI, PLC
AI focus
Train, deploy, monitor, and improve computer vision and machine learning models for battery chemistry classification and automated sorting.
Model-written summary · the original posting is authoritative