AI/ML Inference & Vision Infrastructure Engineer

Front Door Defense; San Francisco, Northern (CA, KY); Hybrid; USD 140,000 - 210,000; Full time

Benefits offered by this job

Restaurant d'entreprise

Indemnités de stage/alternance

Job summary

Zensors in San Francisco seeks an AI/ML Infrastructure Engineer to build and optimize scalable AI inference infrastructure for real-time video analytics.

You will evolve the engine powering our visual sensing platform, accelerate training and inference for CV models, and collaborate across research and platform teams to push throughput while reducing latency.

Applicants should have strong systems programming skills and a track record of delivering performant ML pipelines in production.

Qualifications

• 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.
• Deep understanding of GPU hardware performance, including memory/cache management.
• Experience with profiling/benchmarking tools (Nsight) to validate performance.
• Experience identifying and resolving bottlenecks in high-bandwidth video pipelines.
• Strong communication and cross-functional collaboration skills.

Responsibilities

• Optimizing Core ML Pipelines: identify bottlenecks and optimize for server and edge compute.
• Cross-Stack Collaboration: work with research and platform teams to optimize inference infrastructure.
• Model Acceleration: apply quantization, pruning, and layer fusion to CV models.
• Building Efficient Operators: develop optimized ML operators across PyTorch/CUDA/TensorRT.
• Resource Efficiency: reduce compute cost per video stream for scalability.
• Data Management: support collection and labeling for ML training.

Skills

C/C++

Python

Model optimization

GPU performance

Profiling tools

Video processing bottlenecks

Communication

Education

CS/EE degree

Tools

CUDA

TensorRT

NVIDIA DeepStream

PyTorch

Job description

Zensors in San Francisco seeks an AI/ML Infrastructure Engineer to build and optimize scalable AI inference infrastructure for real-time video analytics.

You will evolve the engine powering our visual sensing platform, accelerate training and inference for CV models, and collaborate across research and platform teams to push throughput while reducing latency.

Applicants should have strong systems programming skills and a track record of delivering performant ML pipelines in production.