Sr. Computational Scientist at NOETIK

THE OPPORTUNITY

At Noetik, you will work alongside a highly technical interdisciplinary team working on hard and impactful problems. Here AI is not a buzzword—it’s the core of our company. We generate our own data, purpose-built for machine learning; we build systems for serious machine learning research; we train large foundation models from scratch; and we center our drug discovery work on these models.

As a Senior Computational Scientist, you’ll work on a team dedicated to understanding which therapeutics work for which patients, in order to immediately improve cancer care. Delivering on these aims will require tight collaboration with our machine learning and therapeutics teams, and will involve full-stack work ranging from model inference to clinical trial simulations. Think of it like building a recommender system, but instead of using sparse behavioral data to predict movie selections, you’ll use the richest cancer dataset in the world to predict drug efficacy.

You’ll work with a high-caliber team who are doing research at the forefront of AI-driven drug discovery & targeting, translating raw multi-modal inference into actionable pipelines. But you’ll also need to navigate the real-world limitations of clinical data, standard-of-care, and small cohort sizes. For that reason we think the most successful candidates will be those with an interdisciplinary background, capable of employing big data where possible, and equipped with the tools to rigorously test their discoveries using approaches from clinical informatics, causal inference, and statistics. We care less about a standard pedigree and more about your ability to bridge disciplines and to engage with problems deeply and urgently. If you have an interesting background and a relentless desire to impact patient outcomes, we would love to hear from you.

KEY RESPONSIBILITIES:

• Architect cancer care recommender engines: spearhead the development of predictive frameworks that act as clinical recommendation engines—mapping complex, multi-modal biological features to the therapeutic assets most likely to eliminate a patient's specific tumor.
• Build blueprints for patient understanding: contribute to or lead projects to identify and describe distinct patient populations who are likely to respond to existing therapeutics.
• Bring causal approaches to AI workflows: Translate large foundation model representations into high-confidence clinical matching systems, applying rigorous statistics and causal inference to validate biological discoveries made in small, heterogeneous datasets.
• Simulate clinical trial success: design and run clinical trial simulations to estimate drug efficacy, identify optimal patient stratification strategies, and maximize the likelihood of success for therapeutic assets.
• Synthesize clinical informatics: make use of messy or fragmented clinical data to understand confounds, extract real biological meaning, and ultimately design better clinical trials.
• Establish and participate in cross-functional best practices: partner tightly with machine learning, engineering, therapeutics, and laboratory teams to define critical scientific questions, decode complex model outputs, and integrate repeated analyses into scalable data processing pipelines.
• Communicate insights: Present complex scientific findings, project milestones, and strategic proposals to both computational and clinical stakeholders, and contribute to peer-reviewed publications and scientific conferences.

QUALIFICATIONS:

• Education & experience: Ph.D. in Biomedical Informatics, Biostatistics, Computational Biology, Computer Science, or a related interdisciplinary scientific discipline with 5+ years of industry experience (or equivalent track record) in oncology or translational drug discovery.
• Interdisciplinary & cross-functional background: a proven capability to bridge distinct scientific domains. We value interesting, non-traditional backgrounds that blend advanced data science with a deep curiosity for cancer biology.
• Statistical & causal Inference rigor: demonstrated experience employing statistical frameworks, causal inference methodologies, or clinical informatics approaches to reliably evaluate and test computational discoveries where data is sparse or limited.
• AI literacy: an operational understanding of vision and/or language foundation models and experience in improving models at scale. Experience with AI coding tools is a plus.
• Biological data literacy: hands-on expertise analyzing high-dimensional biological data. Experience with digital pathology or spatial transcriptomics is highly desirable.
• Technical & coding proficiency: 5+ years of experience coding in Python, with comfort operating at the command line, working with Git version control, and building reproducible, full-stack data analyses.
• Mission-driven urgency: an immense desire to immediately impact patient care, coupled with the flexibility to thrive, pivot, and collaborate effectively in a fast-paced, highly technical research environment.