A Technical Lead Manager role focused on advancing ML infrastructure through quantized training and model compression techniques to optimize autonomous vehicle models at Nuro.
Key Responsibilities
Drive adoption of advanced quantization techniques to optimize model training and deployment.
Set technical strategy for ML training infrastructure and evaluate emerging research methods.
Lead design and implementation of efficiency initiatives such as low-bit quantization, pruning, and knowledge distillation.
Collaborate with research, infrastructure, and product teams to balance accuracy, latency, and resource constraints.
Mentor and develop a team of engineers and researchers specializing in ML infrastructure and model compression.
Requirements
6 years of professional or research experience in ML infrastructure, distributed training, or ML systems engineering
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
Benefits & Perks
Compensation/salary range between $235,030 and $352,290