Nuro is seeking an experienced Technical Lead Manager with deep expertise in quantized training and model compression to join their ML Infrastructure team. The goal is to drive the adoption of state-of-the-art quantization techniques, enabling training and deployment of highly-efficient models that power the Nuro Driver™, and to improve model training efficiency.
Requirements
- Hands-on experience with quantization methods, including Activation-Aware Weight Quantization (AWQ), Accurate Quantized Training (AQT), FP-8 training, or related methods.
- Knowledge of broader model compression techniques, such as structured/unstructured pruning and knowledge distillation.
- Experience building or maintaining quantization libraries(e.g., AQT, bitsandbytes, NVIDIA Transformer Engine, DeepSpeed Compression).
- Understanding of calibration and scaling strategies for quantized models to minimize accuracy loss.
- Knowledge of sparse networks and complementary model compression techniques (e.g., AdaRound, BRECQ, structured pruning).
- Published work or open-source contributions in quantization methods (e.g., AWQ, AQT, GPTQ, SmoothQuant, ZeroQuant).
Responsibilities
- Setting technical direction for the Training Infrastructure team.
- Staying ahead of emerging research and evaluating new methods.
- Establishing telemetry to root-cause quality regressions in lower precision training.
- Driving the adoption of quantized training methods (e.g., AWQ, AQT, GPTQ) across Nuro’s ML infrastructure to accelerate model training and inference.
- Leading the design and implementation of efficiency initiatives for model training, including low-bit quantization, pruning, and knowledge distillation, for both research and production workloads.
- Collaborating cross-functionally with research, infrastructure, and product teams balancing accuracy, latency, and resource constraints.
- Mentoring and growing a high-performing team of engineers and researchers.
Other
- 6+ years of professional or research experience in ML infrastructure, distributed training, or ML systems engineering.
- Advanced degree (Ph.D. or strong M.Sc. with research experience) in Computer Science, Electrical Engineering, or related fields.
- At Nuro, we celebrate differences and are committed to a diverse workplace that fosters inclusion and psychological safety for all employees.
- Nuro is proud to be an equal opportunity employer and expressly prohibits any form of workplace discrimination based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, veteran status, or any other legally protected characteristics.
