AI/ML Inference & Vision Infrastructure Engineer

Frontdoor Defense; San Francisco (CA); 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

AI/ML Infrastructure Engineer

Build and optimize scalable AI inference infrastructure for real-time video analytics

Location: San Francisco, California

About The Role

Machine Learning Engineer In ML Runtime & Optimization

The AI Infrastructure team at Zensors builds the engine that powers our visual sensing platform. We provide the tools to automate the lifecycle of our AI workflow, including model development, evaluation, optimization, deployment, and monitoring across thousands of video streams.

As a Machine Learning Engineer in ML Runtime & Optimization, you will develop technologies to accelerate the training and inference of computer vision models that power smart spaces and cities.

Your responsibilities will include:

• Optimizing Core ML Pipelines: Identifying key bottlenecks in our current video analytics pipeline and performing in-depth analysis to ensure the best possible performance on current server and edge compute architectures.
• Cross-Stack Collaboration: Collaborating closely with AI research and platform engineering teams to optimize core parallel algorithms and influence the design of our next-generation inference infrastructure.
• Model Acceleration: Applying advanced model optimization techniques—such as quantization (Int8/FP16), pruning, and layer fusion—to our Vision Transformers (ViTs) and CNNs to maximize throughput and minimize latency.
• Building Efficient Operators: Working across the entire ML framework/compiler stack (e.g., PyTorch, CUDA, TensorRT, and NVIDIA DeepStream) to write custom optimized ML operator libraries.
• Resource Efficiency: Reducing the compute cost per video stream to enable massive scalability of our SaaS product.
• Data Management: Building, improving, maintaining, and operating systems to facilitate the collection, labeling, and use of 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 the cost/performance trade-offs of video processing.
• Experience with profiling and benchmarking tools (e.g., Nsight Systems, Nsight Compute) to validate performance on complex architectures.
• Experience identifying and resolving compute and data flow bottlenecks, particularly in high-bandwidth video processing pipelines.
• Strong communication skills and the ability to work cross-functionally between research and infrastructure teams.

Preferred Qualifications

• Familiarity with database systems (e.g., SQL, Neo4j).
• Work in Computer Vision, Deep Learning, and Vision Transformers.
• Experience with video processing frameworks such as NVIDIA DeepStream, DALI, or FFmpeg.
• Familiarity with ML compilers (e.g., TVM, MLIR) or inference engines like TensorRT or ONNX Runtime.
• Knowledge of distributed training systems or cloud-scale inference serving (e.g., Triton Inference Server).