📍 Location: Fully Remote (US or Canada)
💰 Compensation: $200K - $260K + equity
🛂 Visa Sponsorship: Not available / case-by-case basis
We’re looking for a senior computer vision engineer who can build image generation models for digital pathology, working across representation learning, image-to-image translation, large-scale training, inference optimization, and clinically reliable deployment on gigapixel whole-slide images.
About PictorLabs
PictorLabs is a digital pathology company building an AI-powered virtual staining platform designed to modernize histopathology and improve patient outcomes.
Its proprietary technology can generate virtual stains from a single unstained tissue sample, producing outputs designed to closely match traditional chemical stains. This enables faster diagnostics, better tissue preservation, reduced chemical waste, and more scalable pathology workflows.
The company is moving from breakthrough R&D into real clinical deployment, including work connected to FDA submissions and regulated healthcare environments.
PictorLabs brings together expertise across bioengineering, artificial intelligence, and health-tech product development.
About Aurora
Aurora helps exceptional engineers discover opportunities at some of the world’s most ambitious startups.
We work closely with companies to identify high-caliber talent and match them with roles where they can have outsized impact.
We’re currently helping PictorLabs grow its machine learning team.
About the role
Senior Applied ML Engineer / Computer Vision Engineer focused on generative models, representation learning, and production ML systems.
It is not a pure research role, and not a generic software engineering role.
The position sits at the intersection of:
- Deep learning research
- Model optimization
- MLOps / deployment systems
- Healthcare-grade reliability
What You’ll Work On
- Design and implement computer vision and deep learning systems for virtual staining and digital pathology
- Build models using Vision Transformers, Diffusion Models, GANs, and image-to-image translation architectures
- Work on segmentation, denoising, image enhancement, latent representations, and large pathology datasets
- Train, fine-tune, evaluate, and productionize foundation models and custom architectures
- Collaborate with engineers, data scientists, and pathology experts to ship research systems into production
- Improve latency, throughput, reproducibility, reliability, and deployment workflows
- Build internal tooling for experimentation, model lifecycle management, and data quality
What We’re Looking For
- 5–10 years of experience as an ML Engineer, Applied ML Engineer, or ML Inference Engineer
- Strong hands-on expertise in computer vision and deep learning
- Experience with one or more of: Vision Transformers, Diffusion Models, GANs, segmentation, image generation
- Excellent Python + PyTorch skills
- Experience with distributed training, cloud ML infrastructure, or production model deployment
- Familiarity with CI/CD, model registries, versioning, data pipelines, and production ML workflows
- Strong communication skills and comfort working in a fast-moving startup environment
Especially Valuable Experience
- Medical imaging / digital pathology / whole-slide imaging (WSI)
- TensorRT / ONNX / Triton / GPU optimization
- Hugging Face ecosystem / LoRAs / fine-tuning workflows
- Kubeflow / MLflow / MLOps systems
- Regulated AI/ML environments or FDA-adjacent workflows
Tech Stack
Python, PyTorch, Computer Vision, Diffusion Models, Vision Transformers, AWS / GCP / Azure, MLOps Infrastructure
Why This Role Is Interesting
You’ll work on technically demanding problems involving:
- Gigapixel pathology images
- Production inference optimization
- Clinically reliable AI systems
- Real deployments with real-world impact
This is the kind of role where strong engineering and strong ML both matter.
If you want meaningful ownership, challenging systems work, and the chance to help shape a category-defining healthcare AI product, we’d love to speak.
