AI Inference & HPC Engineer – Performance & APIs

Topaz Labs; Emeryville (CA); On-site; USD 90,000 - 150,000; Full time

Benefits offered by this job

Full medical/dental/vision coverage

15 days PTO

5 personal days + holidays

401k matching

Equity and profit sharing

Job summary

Topaz Labs is seeking a Software Engineer to support and optimize our AI Engine. You will report to the Head of AI Engine and enhance performance, stability, and feature availability across internal APIs and production products.

You will bridge research and production, preparing new models for deployment and optimizing GPU/CPU workloads. The role requires hands-on experience with C/C++, API design, image processing, and multithreading, along with at least 1 year in a related field.

Qualifications

• Hands-on experience with performance optimization, e.g. concurrency, multithreading, memory, speed, benchmarking, reliability
• Experience architecting APIs for internal development
• Hands-on experience implementing image processing or computational photography algorithms
• Expert knowledge of C/C++
• At least 1+ years of professional working experience in a related field

Responsibilities

• Increase app performance, stability, and availability of new features
• Simplify and improve the API of the framework
• Serve as the technical bridge between the Deep Learning research team and production products
• Help prepare new and updated models for production and assist with GPU/CPU optimization
• Collaborate with hardware partners (NVIDIA, AMD, Intel, Apple) to optimize inference on their hardware

Skills

C/C++

API design

Performance optimization

Multithreading

GPU optimization

Image processing

Benchmarking

Tools

OpenCV

ffmpeg

ONNX

TensorRT

Job description

Topaz Labs is seeking a Software Engineer to support and optimize our AI Engine. You will report to the Head of AI Engine and enhance performance, stability, and feature availability across internal APIs and production products.

You will bridge research and production, preparing new models for deployment and optimizing GPU/CPU workloads. The role requires hands-on experience with C/C++, API design, image processing, and multithreading, along with at least 1 year in a related field.