AI/ML Infrastructure Engineer
San Francisco • FullTime
Posted 5mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
Machine Learning Engineer
About the job
The AI Infrastructure team at Zensors builds the engine that powers our visual sensing platform, providing tools to automate the entire AI workflow from model development to monitoring. As a Machine Learning Engineer, you will focus on developing technologies to accelerate the training and inference of computer vision models, crucial for smart spaces and cities. This role involves optimizing core ML pipelines, collaborating across teams, and applying advanced model optimization techniques to enhance performance and reduce costs.
Responsibilities
- Optimize core ML pipelines by identifying bottlenecks and analyzing performance on server and edge compute architectures.
- Collaborate with AI research and platform engineering teams to optimize parallel algorithms and influence next-generation inference infrastructure design.
- Apply model optimization techniques like quantization, pruning, and layer fusion to Vision Transformers and CNNs to maximize throughput and minimize latency.
- Develop custom optimized ML operator libraries across the ML framework/compiler stack (e.g., PyTorch, CUDA, TensorRT, NVIDIA DeepStream).
- Reduce compute cost per video stream to enable massive scalability of the SaaS product.
- Build, improve, maintain, and operate systems for collecting, labeling, and using visual data for ML training.
Requirements
- BS/MS or Ph.D. in Computer Science, Electrical Engineering, or a related discipline.
- Strong programming skills in C/C++ and Python.
- Experience with model optimization, quantization, and efficient deep learning techniques (e.g., knowledge distillation, pruning).
- Deep understanding of GPU hardware performance, including execution models, thread hierarchy, memory/cache management, and video processing cost/performance trade-offs.
- Experience with profiling and benchmarking tools (e.g., Nsight Systems, Nsight Compute) on complex architectures.
- Experience identifying and resolving compute and data flow bottlenecks, especially in high-bandwidth video processing pipelines.
- Strong communication skills and ability to work cross-functionally between research and infrastructure teams.