Machine Learning Scientist, Computational Pathology
关于我们：阿特拉是一家致力于改变癌症护理的人工智能公司。我们开发了分析临床和病理数据的基础模型，产生可操作见解来指导治疗选择并改善癌症患者的结果。通过不断改进这些模型，我们的目标是发现导致癌症进展的生物机制。构建改变癌症治疗方式的 ML.大多数医学 AI 停止出版。我们的 AI 模型今天引导治疗决策。阿特拉的 AI 驱动前列腺测试在美国都是标准的护理标准，并且50个州的癌症病人正在使用我们的模型帮助他们做出治疗决定。在前列腺癌开始时，我们已经发展成为一个多种癌症平台。你将帮助构建下一步的角色。在 Artera,我们正在做 ML 开发代理第一。你不会花费你的日子写手术训练循环，调节笔记本中的超参数或照顾个人运行。相反，你会设计，指导和评估自主研究机构提出假设，编写和执行实验，并独立培训模型。你将被任务回答特定的科学问题：你的任务将是决定哪些值得研究和哪些研究方向值得投资。平等员工机会：在 Artera,我们重视汇集来自不同背景的人来为患者和医生开发新的创新解决方案。作为平等机会雇主，我们不基于种族，颜色，宗教，民族起源，年龄，性别 （包括怀孕）,身体或精神残疾，医疗状况，基因信息性身份表达，性取向，婚姻状态，受保护的退伍军人地位或任何其他法律保护特征进行歧视.Artera 的工作为什么不同：·你的模型帮助癌症患者。这不是人工智能生成猫视频或定制化爱莫吉斯。我们的工作直接影响那些经历生活中最困难时期中的病人。·基金会模式尺度。我们从零开始训练自己的病理学基础模型，使用 AWS 分布式多节点 GPU 培训。虽然边界实验室可能破解了编码和数学，但它们对我们的问题阅读生物学的能力是不可用的。阿特拉正在研究
查看英文原文
About Us: Artera is an artificial intelligence company dedicated to transforming cancer care. We’ve developed foundation models that analyze clinical and pathology data, generating actionable insights that guide therapy selection and improve outcomes for cancer patients. By continuously improving these models, we aim to uncover the biological mechanisms driving cancer progression.
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.
Equal Employee Opportunity:At Artera, we value bringing together individuals from diverse backgrounds to develop new andinnovative solutions for patients and physicians. As an equal opportunity employer, we do notdiscriminate on the basis of race, color, religion, national origin, age, sex (including pregnancy),physical or mental disability, medical condition, genetic information gender identity orexpression, sexual orientation, marital status, protected veteran status, or any other legallyprotected characteristic.
Why the work is different at Artera:
- 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.
What you'll do:
- 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.
What we're looking for:
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.