D24 Search · 5 hours ago
Senior ML Inference Engineer
D24 Search is an established Series A funded Biotech start up revolutionizing digital pathology with AI-powered virtual staining. They are seeking a Senior Inference System Engineer to optimize and deploy production virtual staining models at scale, focusing on reducing inference latency and ensuring regulatory compliance.
Responsibilities
Analyze AI model architectures to identify and eliminate performance bottlenecks, working closely with ML engineers to update and optimize them
Optimize the entire inference pipeline for processing very large images (e.g., 60k x 60k pixels), including tiling, processing, and stitching
Deploy and host optimized models on various inference platforms, including multi-GPU setups and edge devices like NVIDIA DGX Sparc
Utilize tools like PyTorch, Torch.Compile, and TensorRT to make inference processes highly efficient and performant
Support the team in meeting regulatory compliance requirements such as FDA and SOC 2
Qualification
Required
5 - 10 years of experience as a ML engineer or ML inference engineer at a top tech company
Experience with image processing, ideally for large, high-resolution images (e.g., pathology, drone imagery)
Experience with inference processing
Undergrad in CS from top 100 school
Proficiency in Python, PyTorch and TensorRT
Experience with AWS for hosting and scaling models
Ability to learn quickly in a rapidly changing field
Benefits
Equity
Company
D24 Search
D24 is a boutique recruiting firm offering white glove services for venture backed deep-tech starts ups from seed to IPO and beyond.
Funding
Current Stage
Early StageCompany data provided by crunchbase