Senior Computational Biologist

Are you ready to own the analysis, predictive modeling and interpretation of large-scale perturbation single-cell transcriptomic screens, turning high-dimensional, complex gene expression state changes into clear biological conclusions that drive therapeutic decisions in cardio-renal-metabolic disease?

Large-scale transcriptomic data is at the heart of Gordian's discovery efforts, and the company will succeed based on our ability to accurately predict physiological changes in disease using single cell gene expression as a readout. In this role, you'll help ensure our screening and validation decisions are grounded in rigorous, transparent and state-of-the-art analyses, enabling us to confidently prioritize the best targets and interventions.

About the Role:

Gordian is at an exciting inflection point, having recently generated in vivo perturbation data spanning over 500 targets across different in vivo contexts (Obesity, Heart Failure), and are actively expanding this to Chronic Kidney Disease (CKD). This growing resource is being utilized in collaboration with external partners looking to leverage our platform to help build the most comprehensive knowledge-graph of disease-relevant, translatable therapeutics spanning these disease areas. Your mission as a Computational Biologist at Gordian is to leverage our in vivo screens to decode how cells respond to genetic perturbation at the transcriptomic level, and translate those responses into predictions of physiologically-relevant, therapeutically-actionable outcomes in disease. Based on your work, Gordian will continue to push the frontier of extracting physiological predictions from cell states. You'll specifically focus on cardio-renal-metabolic indications and associated tissues (heart, kidney, adipose, liver, etc.), partnering closely with our disease-area experts and experimental teams to translate screen results into clear, testable biological hypotheses.

Working collaboratively with other computational members, you will guide key analytical decisions across the screen lifecycle - from experimental design and power calculations, to QC thresholds and dataset integration strategies, to the statistical frameworks used for hit calling and prioritization for validation. This includes developing and applying robust methods for modeling heterogeneous biological contexts (e.g., cell-type-specific perturbation responses, animal, batch or treatment context variability), identifying and correcting for confounders (e.g., cell cycle, ambient RNA, doublets, batch effects etc.), and selecting or designing appropriate positive and negative controls to validate effect sizes and method performance. You will communicate findings with rigorous attention to interpretability and generalizability - distinguishing robust, reproducible signal from context-specific artifacts - and ensure that QC metrics, model outputs, and troubleshooting insights flow back to the single-cell and experimental teams to iteratively improve assay design and data generation. You will also help define how we deploy agentic LLM systems to build modular, semi-automated frameworks for in-house QC, analysis, and interpretation - integrating cutting-edge computational methods (e.g., perturbation-response models, trajectory inference, representation learning) with clinically relevant genomic resources to address the specific biological question at hand.

Working in collaboration with our disease experts and in vivo team, you will help connect perturbation-driven molecular changes to in vivo physiology, identifying high-confidence features that capture desirable phenotypes, and build a prioritized set of candidate targets for future screens on the basis of those predictions. Over time, you'll help establish and iterate on selection criteria for validation that improves screening efficiency and translatability across programs.

In your first month, you'll become fluent in our in-house pipelines and workflows and independently propose analysis tasks supporting our Obesity and Heart Failure programs, starting with resource gathering and structured data exploration.

By three months, you'll make significant contributions to feature development and/or validation, including evaluating alternative analytical approaches with appropriate use of controls, statistical testing, and an emphasis on interpretability tied to mechanism-of-action validation.

At six months, you'll help define strong positive and negative controls (indicators) for these screens, partner independently with disease experts on forward screen planning, and use existing validation comparisons to assess predictive power, proposing concrete improvements to analysis methodologies along the way.

About You:

You have a track record of success in high-agency work, consistently creating momentum rather than waiting for direction.

You want to do your best work alongside exceptional teammates and are energized by environments where people push each other to think more clearly, work at a higher standard, and grow into better versions of themselves.

You truly want to play a key role in an early-stage startup screening new targets for intractable diseases of aging: A fast-paced environment full of both uncertainty and new challenges, demanding relentless resourcefulness.

You have a PhD in Bioinformatics, Computational Biology, or a related quantitative field, paired with deep domain expertise in disease biology - you're as comfortable discussing pathophysiology and experimental design with biologists as you are discussing model architecture with computational colleagues.

You have at least 2+ years of hands-on experience (post-graduate) analyzing single-cell transcriptomic data (industry and/or postdoctoral) across different biological contexts, with a proven track record of productivity (at least one peer-reviewed publication or pre-print with a major contribution as co-author relating to a computational method or adapted analysis framework applied to a specific disease-relevant system), and a genuine drive to develop or adapt novel analysis methods rather than rely solely on off-the-shelf pipelines.

You're proactive and excited about new developments in single-cell and functional genomics, human genetics, and computational modeling, and you actively bring promising new methods (e.g. foundation models, perturbation-prediction approaches, trajectory and state-transition modeling, etc.) into your analytical toolkit. You have concrete examples of building or substantially extending methods to answer a specific biological question, especially ones related to mapping cell-state transitions (e.g., across healthy-to-disease trajectories), and want to apply these in the context of in vivo screens.

You treat benchmarking as a first-class part of method development, not an afterthought - you instinctively reach for positive and negative controls to validate new approaches, and when good controls or ground-truth datasets don't exist, you take the initiative to design or source them. You have strong statistical foundations and judgment around controls, confounders, and interpretability in single-cell data

You communicate results through honest, clear visualizations and concise summaries that resonate with both computational and experimental audiences.

You're very proficient in both Python and R for single-cell analysis (e.g., Scanpy, Seurat) and general data analysis, moving fluidly between ecosystems, and you have working familiarity with NGS workflows and common file formats (FASTQ, BAM) sufficient to reason about data provenance and quality - though your focus is on what the data reveals biologically, not on building or maintaining the infrastructure that produces it.

You think constantly about how to scale your own impact - you look for opportunities to standardize recurring analyses into repeatable workflows, and you're excited about using agentic LLM systems to automate or semi-automate these workflows once established, freeing up time for novel method development.

You're an excellent interdisciplinary collaborator: self-motivated, comfortable with ambiguity, and energized by close partnership with experimental teams and domain experts to ground your computational work in real biological questions, particularly around in vivo perturbation studies and disease modeling.

Additional valuable skills if you have them

Experience with pooled perturbation and screening data (for example, CRISPR or barcode-driven screens) and single-cell perturbation analysis methods.

Prior work in cardio-renal-metabolic biology and relevant tissues (heart, kidney, adipose, liver), either directly or through close collaboration with disease experts.

Experience integrating vast public genomics resources with internal data and building scalable workflows for large datasets (HPC and/or cloud).

Experience with preclinical models for validation with functional readouts (e.g. in human explants, organoids, etc)

The Details:

Gordian aims to provide everything you need to thrive. Beyond our community and science, you'll have enough equity to be a true stakeholder in the company, competitive salary, full health/dental/vision/life insurance, 401k with match, onsite lunch paid for 3 days a week, basic onsite gym, whatever vacation you need to be at your peak, and access to world-class mentors and advisors to support your professional growth. Our building is in the heart of the biotech capital of South San Francisco.

The pay range for this role is:

150,000 - 210,000 USD per year (South San Francisco)