AI Inference Engineer - Performance & API

Topazlabs; Dallas (TX); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Full medical/dental/vision coverage

15 days PTO

5 personal days + holidays

401k matching

Job summary

Topaz Labs, a full-stack AI company, is seeking a Software Engineer to support our AI Engine and improve the performance of our internal AI framework. You will bridge the Deep Learning research team with production products, and optimize GPU/CPU paths while preparing models for deployment.

You will collaborate with hardware partners such as NVIDIA, AMD, Intel, and Apple to optimize inference and enhance image processing capabilities. This is a full-time onsite role in Dallas, TX.

Qualifications

• Strong C/C++ expertise and system-level optimization.
• Experience with performance optimization, concurrency, multithreading.
• Experience with image processing/photography algorithms.
• Experience with OpenCV, ffmpeg and GPU programming.
• Experience with video encoding/decoding and file formats.

Responsibilities

• Improve performance of the internal AI Engine and APIs.
• Bridge between DL research and production products.
• Prepare models for production and optimize for GPU/CPU.
• Collaborate with hardware partners (NVIDIA, AMD, Intel, Apple) for inference optimization.

Skills

Performance optimization

APIs for internal development

Image processing algorithms

C/C++ expertise

Professional experience 1+ years

Video encoding/decoding

OpenCV & FFmpeg

GPU programming

Raw image pipeline

ONNX/CoreML/TensorRT

Photography / videography interest

Job description

Topaz Labs, a full-stack AI company, is seeking a Software Engineer to support our AI Engine and improve the performance of our internal AI framework. You will bridge the Deep Learning research team with production products, and optimize GPU/CPU paths while preparing models for deployment.

You will collaborate with hardware partners such as NVIDIA, AMD, Intel, and Apple to optimize inference and enhance image processing capabilities. This is a full-time onsite role in Dallas, TX.