Skip to content
Topaz LabsTopaz LabsDallas, TX

Software Engineer, AI Inference / HPC

Develops and optimizes AI inference engine for image/video enhancement, focusing on performance, GPU/CPU optimization, model deployment, and hardware partnerships. Requires C/C++ expertise, 1+ years experience in performance optimization and image processing.

110k – 150k/yr
On-site1+ YOEML Engineering

About the role

Responsibilities

  • Improve performance, stability, availability of new features, and simplify/improve the API of the internal AI Engine framework.
  • Act as technical bridge between Deep Learning research team and Production products.
  • Prepare new & updated models for production.
  • Optimize GPU/CPU for inference.
  • Work with hardware partners (NVIDIA, AMD, Intel, Apple) to optimize inference on their hardware.

Requirements

  • Hands-on experience with performance optimization (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.

Preferred

  • Experience with video encoding/decoding and file formats.
  • Experience with OpenCV, ffmpeg, GPU programming.
  • Experience with raw image camera pipeline and image formats.
  • Experience with ONNX, CoreML, TensorRT runtime SDKs.
  • Interest in photography or videography.

Skills

C++CPerformance OptimizationMultithreadingConcurrencyAPI DesignImage ProcessingOpencvFfmpegGpu ProgrammingOnnxCoremlTensorRT

Similar roles

ML Engineering jobs
PathAI

Machine Learning Engineer II/III (Applied Research & Model Development)

PathAIBoston, MA +1

Designs, develops, and deploys ML models for research and product development in pathology AI, collaborating with scientists and engineers on biological/clinical applications. Requires Master's/PhD, Python/ML expertise, production deployment experience; leads projects at senior levels.

107k – 200k/yr
Hybrid2+ YOEML Engineering
Ai2

Research Engineer, Asta

Ai2Seattle, WA

Research Engineer builds ML infrastructure and agentic systems to accelerate scientific discovery in biology, neuroscience, and more. Requires 2+ years experience with Python, PyTorch/JAX/TF, cloud resources, and deep learning for LLM/agent research at Ai2.

119k – 178k/yr
On-site2+ YOEML Engineering
Trexquant

Quantitative Researcher

TrexquantNew York, NY

Early-career Quantitative Researcher developing ML models and trading signals to predict asset movements and build market-neutral portfolios. Requires STEM degree, Python fluency, and passion for machine learning; embedded in Alpha, Data Science, or Strategy teams.

120k – 180k/yr
On-siteEntry levelML Engineering
Mariana Minerals

Machine Learning Engineer

Mariana MineralsAnn Arbor, MI +2

Build and deploy reinforcement learning models to autonomously control mineral refining facilities, optimizing recovery rates, energy use, and uptime in real operating plants.

120k – 160k/yr
On-siteEntry levelML Engineering
Bild AI

Founding AI Engineer

Bild AISan Francisco, CA

Founding AI Engineer building and shipping production-grade computer vision, LLM, and multimodal models for real-world construction documents at an early-stage startup.

120k – 180k/yr
On-siteEntry levelML Engineering