Job Description

About Us:

Grafton Biosciences is a stealth-mode, San Francisco-based biotech startup focused on solving disease through groundbreaking innovations in early detection and therapeutics. We are combining breakthroughs in synthetic biology, machine learning, and manufacturing to fundamentally extend healthy human lifespans. We’re looking for passionate team members who want to shape the future.

Role: Senior Bioinformatics & Machine-Learning Data Scientist

We are seeking a highly specialized scientist who thrives at the intersection of machine learning, bioinformatics, and data engineering. Your mission will be to build and adapt cutting-edge analytical pipelines that transform petabyte-scale multi-omics data into actionable biological insight. From raw sequencing reads to integrated molecular models, you will design the engines that fuel our discovery platform. The ideal candidate is not just a data scientist, but a computational biologist who can architect scalable infrastructure, craft sophisticated models, and collaborate seamlessly with wet-lab teams to drive novel therapeutics.

Key Responsibilities

• Design, implement, and optimize end-to-end bioinformatics pipelines (e.g., Nextflow, Snakemake, Cromwell) for high-throughput genomics, transcriptomics, epigenomics, and single-cell assays.
• Develop and apply advanced machine-learning / statistical models (including deep learning, probabilistic graphical models, and transformer-based architectures) to uncover biomarkers, predict functional effects, and stratify patient populations.
• Engineer distributed data architectures (Spark, Dask, cloud object stores, GPU clusters) that enable rapid querying and analysis of terabyte- to petabyte-scale datasets.
• Curate, harmonize, and QC diverse public and proprietary datasets , establishing robust data schemas, metadata standards, and version-controlled repositories.
• Integrate multi-omics layers (DNA, RNA, protein, spatial, clinical) into unified representations that power target discovery and mechanism-of-action studies.
• Collaborate deeply with experimental biologists and chemists to translate computational insights into testable hypotheses and guide iterative experimental design.
• Stay at the forefront of the field by tracking breakthroughs in large-scale data analytics, generative biology, and cloud-native bioinformatics—and rapidly prototyping relevant approaches.

Qualifications

To address the specific needs of this role, candidates must demonstrate experience in the following core areas. Applications without this experience will not be considered:

• Must-Have: Large-Scale Biological Data Expertise. Proven experience designing and maintaining pipelines for complex, high-volume biological datasets (e.g., whole-genome sequencing, single-cell RNA-seq, spatial transcriptomics, proteomics). You understand both the algorithms and the underlying biology.
• Must-Have: Scalable Machine Learning & Data Engineering. Hands-on mastery of distributed computing (Spark, Ray, or similar) and cloud platforms (AWS or Azure). Demonstrated ability to train, tune, and serve large models on heterogeneous biological data.

Essential Qualifications

• Ph.D. or Master’s in Bioinformatics, Computational Biology, Computer Science, Biostatistics, or related field with a strong focus on biological applications.
• Fluency in Python (preferred) and one or more statistical languages (R, Julia).
• Experience with workflow managers, containerization (Docker/Singularity), and CI/CD for reproducible science.
• Solid grounding in statistics, experimental design, and multi-omics data integration.
• Proficiency with relational and NoSQL databases, graph databases a plus.
• Clear communication skills and a collaborative mindset; you can translate data insights into biological impact.

Preferred Qualifications

• Big Plus: Expertise in dimensionality-reduction and visualization of massive high-dimensional datasets (e.g., UMAP, t-SNE, tensor decomposition).
• Familiarity with reinforcement learning or generative models for biological sequence design.
• Experience contributing to or maintaining open-source bioinformatics software.
• Publications in top-tier ML or computational biology venues (e.g., NeurIPS, ICML, ICLR, ISMB, Cell Systems, Nature Methods).
• Background in knowledge-graph construction or network biology.

What We Offer

• Competitive compensation.
• Comprehensive health, dental, and vision coverage.
• The opportunity to define a new data-driven therapeutic design paradigm—and see your work progress toward the clinic.

Screening Questions

If you are a particularly good fit for this role , please email careers@graftonbio.com with responses to the following questions. The email subject should be: Bioinformatician - [Your Last Name].

(1) In ≤400 words, walk us through a project where you engineered an end-to-end pipeline that processed terabyte-scale biological data (genomics, single-cell, proteomics, etc.). Please cover:

1. What scientific question or decision did the pipeline enable?
2. Rough size, modality mix, and the toughest quality-control challenges you had to solve.
3. Pipeline architecture: Workflow manager(s) (e.g., Nextflow, Snakemake, Cromwell), container/CI setup, and the storage/compute stack (cloud services, distributed file systems, GPU/CPU mix).
4. Your personal contributions (key pieces of code or optimizations you authored).
5. Outcome & validation: Quantitative performance metrics (runtime, cost, accuracy) and the downstream biological insight or product milestone it unlocked.

We’re looking for evidence that you can own both the scientific rationale and the engineering required to make large-scale data analysis reliable and reproducible.

(2) Provide concise bullet points (≤400 words total) detailing one instance where you trained or served a large machine-learning model on heterogeneous biological data in a cloud or distributed environment. Please cover:

• Type of model (e.g., transformer, GNN, probabilistic model) and the biological prediction or discovery goal.
• Frameworks used (Spark, Ray, Dask, Horovod, PyTorch DDP, etc.), cluster size, and how you handled memory, scheduling, or GPU utilization.
• How you organized, partitioned, and tracked multi-omics inputs across iterations.
• Training/serving speed-ups, cost savings, or accuracy improvements achieved (include numbers).
• How the model was integrated into downstream analyses, visualization dashboards, or experimental decision-making.

We want to see concrete evidence that you can push large models through cloud-scale infrastructure and connect their outputs back to actionable biology.

Job Tags

Similar Jobs