Deep Learning Engineer: Computer Vision

Resolute Bio; København; On-site; DKK 700,000 - 950,000; Full time

Job summary

Resolute Bio is seeking a Deep Learning Engineer to lead computational pathology efforts on the tileDVP platform. You will work with whole-slide images at scale, turning gigapixels of tissue into biological insight within a mission-driven team in central Copenhagen.

You'll employ modern vision models, collaborate with biologists, and bring production-minded engineering practices to model development, evaluation, and deployment, while leveraging toolchains for tracking and reproducibility.

Qualifications

• Education at MSc or PhD in Computer Science, Engineering, or a related field.
• 2–5 years of experience training, evaluating, and fine-tuning the latest generation of vision models - industry experience is valued

Responsibilities

• Develop and optimize deep learning models for histology slide segmentation and region-of-interest identification
• Train, evaluate, and fine-tune modern vision models on both large-scale public datasets and our proprietary data
• Work with whole-slide images in open formats (e.g., OME-TIFF, OME-Zarr) using tools such as LazySlide and the AnnData/SpatialData ecosystem
• Build and maintain infrastructure for model tracking, evaluation, and versioning
• Integrate models into our containerized production environment together with the software team
• Continuously research and adopt the latest advances in computer vision applicable to histopathology
• Work closely with biologists and domain experts to incorporate biological insight into model development

Skills

Python

PyTorch

Deep learning

Linux

Docker

Experiment tracking

Education

MSc or PhD in Computer Science, Engineering, or a related field

Tools

Docker

OME-TIFF

OME-Zarr

LazySlide

AnnData/SpatialData

Weights & Biases

Neptune.ai

MLflow

Job description

Ready to Push the Frontiers of AI-Powered Spatial Proteomics?

Computer vision has learned to read human tissue biology. Pathology foundation models trained on millions of slides can embed, cluster, and classify histology with remarkable skill - but they have all learned from the image alone. The proteins that actually drive disease have never been part of the training signal, because this data has never existed at scale.

That's where Resolute Bio comes in. On our tileDVP platform, regions of a slide are linked to deep proteomic measurements from the very same tissue - gigapixels of morphology, grounded in molecular ground truth. We build the virtual tissue models that decide where to look, what to measure, and what the tissue is telling us.

If you are excited about applying modern computer vision to something that genuinely matters for patients - and don't mind helping us drive up our compute and GPU bills along the way - we would love to hear from you!

The Role

As a Deep Learning Engineer, you will lead our computational pathology efforts on the tileDVP platform, building and refining AI models supercharged with proteomics data. You will join a small, international team in central Copenhagen, working with whole-slide images at scale and turning gigapixels of tissue into biological insight - in mission-driven work that translates into real differences in patient care, not just publications. We are an AI-forward team: we use agentic tools daily and expect you to be fluent with them - but the judgment about what to train, whether a model can be trusted, and when the data is telling you something is off still comes from you.

You Will

• Develop and optimize deep learning models for histology slide segmentation and region-of-interest identification
• Train, evaluate, and fine-tune modern vision models on both large-scale public datasets and our proprietary data
• Work with whole-slide images in open formats (e.g., OME-TIFF, OME-Zarr) using tools such as LazySlide and the AnnData/SpatialData ecosystem
• Build and maintain infrastructure for model tracking, evaluation, and versioning
• Integrate models into our containerized production environment together with the software team
• Continuously research and adopt the latest advances in computer vision applicable to histopathology
• Work closely with biologists and domain experts to incorporate biological insight into model development

You Have

Education & Experience

• MSc or PhD in Computer Science, Engineering, or a related field
• 2-5 years of relevant experience training, evaluating, and fine-tuning the latest generation of vision models - industry experience is highly valued

Technical Expertise

• Expert Python programming for data science and machine learning, with strong PyTorch proficiency
• Deep understanding of feature embeddings and their practical use in visualization, clustering, and classification
• Experience handling large-scale image data, ideally gigapixel or whole-slide images and open imaging formats
• Comfort with Linux and containerized workflows (e.g., Docker)
• Familiarity with experiment tracking and model versioning tools (e.g., Weights & Biases, Neptune.ai, MLflow)

Mindset & Skills

• Strong problem-solver who thrives in a fast-paced, ambitious environment
• Clear communicator, able to bridge deep learning and biology across interdisciplinary teams
• Independent in your day-to-day work, while collaborating closely across teams
• Pragmatic and production-minded, with well-organized, reproducible engineering practices
  

Nice to Have

• A strong competitive ML track record (e.g., Kaggle) demonstrating your ability to extract every drop of signal from a dataset
• Experience with biological or medical data, especially digital pathology or spatial proteomics foundation models (e.g., UNI, Virchow, H-optimus, Prov-GigaPath; KRONOS, VirTues)
• Experience with cross-modal models that predict molecular readouts from histology (e.g., GigaTIME, ROSIE, HEX) or CLIP-style multimodal alignment
• Familiarity with ML infrastructure and MLOps - experiment tracking, training pipelines, feature/data stores
• Publications, open-source contributions, or a public portfolio in relevant fields
  

Interested?

• Want to learn more about us first? Visit resolute.bio to see what we are building.