Note: The job is a remote job and is open to candidates in USA. PictorLabs is hiring a Senior Machine Learning Engineer to own the representation-learning and generative-modeling stack behind its virtual staining technology. The role develops and evaluates production-ready computer vision models for digital pathology and collaborates across engineering, data science, and pathology teams to deploy them in clinical workflows.

Responsibilities

• Design and implement novel computer vision and deep learning algorithms for virtual staining and digital pathology applications
• Conduct rigorous experiments to evaluate algorithm performance, validate research hypotheses, and drive iterative improvements
• Develop and advance ML models leveraging Vision Transformers, Diffusion Models, GANs, and generative architectures for image-to-image translation tasks
• Apply classical and learned image enhancement, denoising, and semantic segmentation techniques to histopathology imaging challenges
• Explore image representation in latent space for efficient, high-fidelity virtual staining
• Stay current with state-of-the-art research, identifying opportunities to apply novel techniques to PictorLabs’ product roadmap
• Collaborate with ML Engineering and software teams to translate research prototypes into production-ready systems meeting latency and throughput requirements
• Work with large-scale pathology datasets to train, validate, and fine-tune foundation models and custom architectures
• Partner with software engineers, data scientists, and pathology domain experts to integrate research into production systems
• Contribute to best practices for data engineering, data governance, and data quality across research and production pipelines
• Leverage AI coding and ideation tools to accelerate research velocity and prototype new approaches
• Develop tools and frameworks to streamline ML research workflows, experimentation, and reproducibility

Skills

• PhD
• Master's degree in Computer Science, Electrical Engineering, or a related field
• Deep expertise in computer vision and deep learning, with hands-on experience in one or more of: Vision Transformers, Diffusion Models, GANs, semantic segmentation, or classical image enhancement and denoising
• Expert proficiency in Python and PyTorch
• Strong mathematical foundation in linear algebra, probability, and optimization
• Experience with large-scale model training, distributed computing, or cloud ML infrastructure (AWS, GCP, or Azure)
• Knowledge of handling large scale image data,  data version controls,  model registry, has experience dealing with ML lifecycles
• Experience with feature search, data balancing, and data curation pipelines
• Knowledge of software engineering best practices including version control (Git) and CI/CD pipelines
• Excellent collaboration and communication skills, with the ability to work effectively in a fast-paced, cross-functional international startup environment
• Extensive use of AI tools for coding, optimization, and ideation
• Experience with medical imaging, digital pathology, or whole slide image (WSI) processing
• Experience with LoRAs,  transformer architecture and state of the art image to image translation models (Flux 2, Z-Image) and the Hugging face ecosystem
• Background in generative models and fine-tuning of foundation models
• Experience with GPU acceleration and optimization, including CUDA kernel engineering, TensorRT/ONNX export, and inference serving frameworks such as Triton
• Experience with hosting  computer vision model inference on NVIDIA DGX Spark
• Understanding of FDA regulatory requirements for AI/ML in medical devices
• Experience with MLOps tools (MLflow, Kubeflow) and model versioning practices

Benefits

• Fully remote role for US/Canada based candidates
• Equity
• The opportunity to work on technology that directly improves patient outcomes and transforms clinical diagnostics
• Freedom to pursue high-impact research while seeing your work deployed at scale in real clinical environments

Company Overview