AI/ML Infrastructure Engineer

This job was selected by the SpringCube team to help AI, Data and Cloud Engineers discover relevant San Francisco Bay Area employers. Sign up to view the full employer details and apply directly with the hiring company.

Company Overview

A technology organization is developing a visual sensing platform designed to power smart spaces and cities through advanced computer vision and artificial intelligence. Its AI Infrastructure team builds the underlying systems that automate the machine learning workflow, including model development, evaluation, optimization, deployment, and monitoring across thousands of video streams.

The organization is seeking an AI/ML Infrastructure Engineer to work within its ML Runtime & Optimization function. This role will focus on developing technologies that accelerate the training and inference of computer vision models while improving performance and resource efficiency across server and edge computing architectures.

The successful candidate will work closely with AI research and platform engineering teams to optimize machine learning infrastructure, improve inference performance, and develop highly efficient systems capable of supporting large-scale video analytics workloads.

Key Responsibilities

Core ML Pipeline Optimization

• Identify key bottlenecks within video analytics pipelines and conduct in-depth performance analysis.
• Optimize ML pipelines for current server and edge computing architectures.
• Analyze compute and data flow performance to improve throughput and reduce latency.

Cross-Stack Collaboration

• Collaborate closely with AI research and platform engineering teams.
• Optimize core parallel algorithms and contribute to the design of next-generation inference infrastructure.
• Work cross-functionally to translate research requirements into efficient production infrastructure.

Model Acceleration

• Apply advanced model optimization techniques, including Int8 and FP16 quantization, pruning, and layer fusion.
• Optimize Vision Transformers (ViTs) and convolutional neural networks (CNNs).
• Improve model throughput while minimizing inference latency and computational requirements.

ML Operators & Infrastructure

• Work across the ML framework and compiler stack, including PyTorch, CUDA, TensorRT, and NVIDIA DeepStream.
• Develop custom, optimized machine learning operator libraries.
• Improve the efficiency and performance of ML workloads across GPU-based architectures.

Resource Efficiency

• Reduce compute costs per video stream to support large-scale SaaS deployments.
• Identify opportunities to improve resource utilization across video processing and inference workloads.
• Develop scalable infrastructure capable of supporting thousands of concurrent video streams.

Data Management

• Build, improve, maintain, and operate systems supporting the collection and labeling of visual data.
• Develop infrastructure that enables efficient use of visual datasets for machine learning training.
• Support reliable data workflows for computer vision model development and optimization.

Required Qualifications

• Bachelor’s, Master’s, or Ph.D. degree 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 such as knowledge distillation and pruning.
• Deep understanding of GPU hardware performance, including execution models, thread hierarchy, memory and cache management, and video-processing cost/performance trade-offs.
• Experience with profiling and benchmarking tools such as Nsight Systems and Nsight Compute.
• Experience identifying and resolving compute and data flow bottlenecks in high-bandwidth video processing pipelines.
• Strong communication skills and the ability to collaborate effectively across research and infrastructure teams.

Preferred Qualifications

• Familiarity with database systems such as SQL and Neo4j.
• Experience working in computer vision, deep learning, and Vision Transformers.
• Experience with video processing frameworks such as NVIDIA DeepStream, DALI, or FFmpeg.
• Familiarity with ML compilers such as TVM or MLIR.
• Experience with inference engines such as TensorRT or ONNX Runtime.
• Knowledge of distributed training systems or cloud-scale inference serving technologies such as Triton Inference Server.

Disclaimer

SpringCube curates tech job listings from various company websites to support tech professionals globally.

1.No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.

2.No Client Relationship: This company is not a client of SpringCube unless stated.

3.To Apply: Click the “Apply” button to be redirected to the hiring company’s application page for this job.

4.No Liability: SpringCube is not liable for inaccuracies.**