Director of Computational Biology

Transcripta Bio is a preclinical-stage AI drug discovery company pioneering a patient-first approach to therapeutics. Headquartered in Palo Alto, CA, we have built a proprietary closed-loop discovery engine - comprising our Disease Signature Atlas, Drug-Gene Atlas, and Conductor AI platform - that integrates single-cell patient transcriptomics, causal human genetics, and pre-validated chemistry to identify and advance drug candidates with a structural edge over conventional approaches.

Computational biology is the analytical backbone of everything we do. We build disease signatures from transcriptomic datasets and pair them with our high-throughput drug screens to determine which hypotheses to test and which programs to move forward.

We are looking for a Director of Computational Biology to lead this function. This is a founding leadership role: you will set our computational strategy, build and mentor a team, and serve as the critical bridge between our AI/ML platform and wet lab operations. If you are a biologically-grounded computational scientist who wants to do science that matters and has the leadership instincts to build something from the ground up, this role is for you.

WHAT YOU’LL DO

• Define and execute the computational biology strategy that connects our disease signature pipeline, high-throughput drug screens, and downstream validation experiments to actionable therapeutic insights.
• Lead the analysis of high-dimensional datasets from perturbational screens - including bulk and single-cell RNA-seq, high-content imaging, and protein quantification - to identify hit compounds, validate targets, and characterize the mechanism of action.
• Build, manage, and mentor a team of computational biologists and bioinformaticians; develop their scientific careers and hold the team to a high standard of rigor and reproducibility.
• Develop and maintain scalable, reproducible computational pipelines for data processing, QC, analysis, and visualization across all experimental modalities.
• Partner closely with wet-lab scientists to design experiments, establish data standards, and interpret results in a disease context, ensuring computational outputs drive real decisions.
• Collaborate with AI/ML colleagues to integrate computational biology outputs into the Drug-Gene Atlas and Conductor AI framework; help shape how machine learning interacts with biological discovery.
• Serve as a senior scientific voice internally and externally: present findings to leadership, partners, and the broader scientific community; contribute to publications and IP.
• Identify and evaluate new computational methods, tools, and data sources that could accelerate our platform or expand our therapeutic reach.

WHAT YOU’LL BRING

• PhD in Computational Biology, Bioinformatics, Systems Biology, Genomics, Computer Science, or a closely related field, with 10 years of experience in drug discovery or biotech, including at least 3 years leading or managing scientific teams.
• Deep expertise in transcriptomics - particularly bulk and single-cell RNA-seq - and demonstrated ability to move from raw data to mechanistic biological insight.
• Proven experience analyzing data from perturbational or high-throughput phenotypic screens (e.g., chemical, genetic, or combined drug-gene perturbations).
• Fluency in relevant scientific packages (e.g., scanpy, DESeq2, seurat) and familiarity with workflow management tools (e.g., Snakemake, Nextflow) and cloud computing environments; programming skills in Python and/or R a plus.
• Track record of building and maintaining reproducible, production-quality analysis pipelines in a collaborative, version-controlled environment.
• A biological intuition that goes beyond standard pipelines - you build mechanistic models and interpretations, not just lists of differentially expressed genes.
• Demonstrated leadership: ability to set scientific direction, align cross-functional stakeholders, and develop the scientists around you.
• Excellent communicator: you can translate complex computational concepts for bench scientists, leadership, and external partners with equal clarity.

NICE TO HAVE

• Experience with multimodal data integration (e.g., imaging transcriptomics proteomics).
• Background in rare genetic disease, neurological disease, or genetically defined disease areas with clear causal mechanisms.
• Familiarity with functional genomics approaches: CRISPR screens, perturb-seq, or CRISPRi/a.
• Experience working with or alongside ML/AI teams to build predictive models on biological data.
• Strong publication or patent record in computational drug discovery or related fields.