Machine Learning Scientist, Computational Pathology

Build ML that changes how cancer is treated.

Most medical AI stops with a publication. Our AI models guide treatment decisions today.

Artera’s AI-driven prostate test is standard-of-care in the US and cancer patients in all 50 states are using our models to help make decisions about their therapy. While we started in prostate cancer, we’ve grown into a multi-cancer platform with more disease settings in development. You'll help build what's next.

The role

At Artera, we’re making ML development agent-first. You won’t spend your days hand-writing training loops, tuning hyperparameters in notebooks, or babysitting individual runs. Instead, you’ll design, direct, and evaluate autonomous research agents that propose hypotheses, write and execute experiments, and train models autonomously. You’ll be tasked with answering specific scientific questions: which patients can safely forgo aggressive treatment or inferring molecular traits from routine digital slides and your job will be to decide what’s worth investigating and which research directions merit investment.

Your models help cancer patients. This isn’t AI for generating cat videos or customized emojis. Our work directly affects patients who are experiencing among the most difficult periods of their lives.

Foundation-model scale. We train our own pathology foundation models from scratch with distributed multi-node GPU training on AWS. While frontier labs may have cracked coding and math, their ability to read biology for our problems is unusable. Artera is working on the cutting edge of this space.

Build and evaluate AI models that predict patient outcomes and treatment benefit from whole-slide images and clinical data, or infer molecular traits directly from slides.

Push the frontier in terms of our pan-cancer self-supervised pathology foundation models.

Manage coding agents to propose and execute experiments, improve the efficiency of our tooling, and identify biological insights that explain our models behavior.

Review findings with product, medical, and biostatistics teams, and contribute to regulatory documentation that gets models into patients’ hands.

Co-author papers and share your work at conferences.

You might be a few years into industry or finishing graduate research. Either way, we're looking for someone who has built ML that holds up on real data and has some grounding in biology or medicine.

1+ years building deep learning models (we use PyTorch), in industry or in substantial graduate research

Hands-on experience with coding agents like Cursor or Claude Code.

Experience taking models beyond a notebook and evaluating them rigorously on messy, real-world data

A background in oncology, biology, or biomedical science, from coursework, research, or work (e.g., a biology or bioengineering degree, computational biology research, or ML work in healthcare or biotech)

Clear communication and an interest in working closely with product, medical, and biostatisticians

If you meet most of this and the work excites you, we'd love to hear from you.

Nice to have: large-image computer vision or medical imaging; self-supervised learning; weakly supervised learning (e.g., MIL); survival analysis; domain shift and robustness.

You don't need: a PhD or regulatory experience. You'll learn the regulatory side here, and we'll deepen your oncology knowledge on the job.

How you'll grow: close collaboration with senior ML scientists and engineers, experience across the full lifecycle of a regulated clinical ML product, and room to grow into leading a workstream.