VitVio is building AI-powered tools to simplify and streamline operating room workflows, so surgical teams can focus on what really matters—patient care. Our platform uses computer vision and context-aware AI to understand actions happening in the OR in real time. From automatically logging surgical stages to coordinating team readiness, we take on the administrative load so clinical staff don’t have to.
Our team has experience founding and scaling leading companies in adjacent industries. We're growing quickly—backed by top-tier investors—and working with some of the most respected hospitals in the US and Europe.
About the OpportunityWe're looking for a Machine Learning Engineer with a strong background in Computer Vision to join our experienced engineering team. This role blends deep technical work on our ML models with an active product mindset and offers the chance to build tools used directly in surgical care.
This role is remote-first, and open to European timezones — we prioritize talent over everything else. Some travel (US and Europe) is required to visit hospitals, observe workflows, and co-design with clinical users.
What You’ll DoLike all our engineers you will work across the stack on systems used by hospital staff in high-stakes environments. From RFC to deployment, you’ll take ownership of features, propose creative improvements, and ship clean, reliable code with confidence. As a machine learning engineer, you will be iterating quickly to identify promising model architectures to expand capabilities in line with product direction and bring them into production. You will also work with the wider software team to improve engineering excellence throughout the stack.
In your first 6 months, you will:
Identify and explore promising directions in ML to contribute to our product development
Design, train, and evaluate SOTA model architectures to validate your hypotheses
Experiment, prototype and iterate based on evidence to productionise your ideas
Work with our software engineering team, to strengthen our data and ML infrastructure
Analyse model performance, identify bottlenecks, to improve accuracy, efficiency, and robustness.
Own and ship projects end-to-end maintaining reliability and quality of models and code.
Your primary focus will be on our machine learning systems, especially computer vision models, but as part of a small and collaborative team, you’ll occasionally contribute to other parts of the stack when needed:
ML & Computer Vision: PyTorch, C++, Rust, GStreamer, video processing, multi-view geometry
Backend & Infrastructure: Elixir (Phoenix), GCP, NixOS
Data & APIs: Postgres, GraphQL, REST, healthcare integrations (e.g., HL7/FHIR)
Frontend: React, TypeScript
Although we are looking for extensive computer vision experience (i.e. video processing, PyTorch and multi-view geometry), we don’t expect you to have deep experience in each tool and language listed above. But we’re looking for curiosity and adaptability. We support engineers in learning new tools as needed. So, if you don’t have experience with some of the tech above, no problem, we’d still love you to apply!
You Might Be a Great Fit If You...Know how to pragmatically develop and deploy computer vision models in industry.
Are experienced in multi-view geometry, video streams, and PyTorch.
Are a well-rounded engineer with experience and interest across the stack (our philosophy is for all engineers to contribute to all repositories, at least from time to time).
Are known for writing clean, reliable code and communicating proactively.
Take initiative: when something’s broken, you fix it or flag it.
Think in systems and edge cases, yet move quickly and pragmatically.
Thrive in teams that value candid discussion, curiosity, and mutual respect.
Include the word ‘reactor’ in your application (to let us know you’ve read this).
Find purpose in building software that solves real problems for real people.
We don’t expect you to know all of our stack or match every bullet here — we care more about how you think, learn, and collaborate.
Benefits📈 Early-Stage Equity
💰 Competitive salary
💻 Company laptop along with tools you need to succeed
🧠 Learning & development budget
🎉 Offsites and team-building events (last one was in Crete, Greece!)
🌴 Flexible PTO
Hiring ProcessReview: Submit your application
First Call (30 min): A call with our CTO to talk through your current/past experience, your motivations and tell you more about VitVio.
Meet with our CEO (30 min): You’ll speak to our CEO to see if the magic is there.
Coding Interview (90 mins): You’ll be working with two of our team members through a coding exercise.
Career Deep Dive (90 mins): Our CTO will go with you through your achievements and learnings of your career so far.
ML Interview (90 mins): You’ll be showing us how you are choosing and implementing ML models to solve business requirements
Offer
Top Skills
What We Do
VitVio uses computer vision and ambient sensing to digitize operating rooms in 3D in real-time, providing clarity on who is doing what, when, and why during surgery. Our system then deploys AI agents to handle routine tasks—like automatically logging surgical phases, coordinating staff, and preparing op-notes. The aim is to improve hospital ROI by increasing the OR utilization rate, improving billing accuracy, and reducing administrative burden on medical teams.
Get staff focused on the patient, we'll handle the rest.
Developed by a team with deep expertise in computer vision, AI, and healthcare, looking to embrace the future of healthcare technology.
