Senior / Staff Computational Scientist

Twist Bioscience•South San Francisco, CA

2h•$173,000 - $200,000•Hybrid

About The Position

Twist is seeking a Sr./Staff Computational Scientist to join our Scientific Computing team and help scale Twist Solutions. You will build computational systems and analysis workflows that sit directly on the critical path of antibody programs This is a builder role for someone who enjoys owning ambiguous problems end to end and delivering durable solutions used by scientists and operations teams every day. You will collaborate closely with wet-lab scientists, assay development, QC, software engineers, and ML partners. Some overlap with applied AI/ML is expected and beneficial, especially where models can improve triage, quality, consistency, and scale. Job title and compensation will be determined based on several factors, including but not limited to the candidate's years of experience, individual skills, knowledge, and abilities.

Requirements

MS with 8–12 years of industry experience, or PhD with 4–8+ years of industry experience (or equivalent) in Computational Biology, Bioinformatics, Biophysics, Immunology, Protein Engineering, Machine Learning, Computer Science, or a related field.
Strong grounding in antibody science and engineering concepts, with the ability to reason about antibody sequence, format constraints, and developability considerations.
Strong Python programming skills (pandas, numpy, scipy) and a track record of shipping tools that automate scientific workflows.
Experience working with experimental datasets, applying quantitative methods, and building QC frameworks that produce reliable, consistent outputs.
Comfort collaborating cross-functionally with wet-lab and engineering teams, and ability to translate scientific intent into pragmatic, usable software.

Nice To Haves

Experience with engineered antibody formats (for example bispecific or multi-specific constructs) and challenges around representation, pairing, and assessment.
Applied ML experience, such as feature engineering, evaluation, baselines, model development, or integrating models into production workflows using scikit-learn and/or PyTorch/TensorFlow.
Experience interfacing with lab systems and data sources (for example LIMS, lab automation, instrument data exports).
Familiarity with containers and cloud tooling (for example Docker and AWS/GCP).

Responsibilities

Build and own antibody sequence intake and screening workflows that evaluate sequence integrity, format expectations, and manufacturability risks, producing clear, explainable outputs with traceable evidence.
Develop antibody-aware annotation and feature extraction that supports common antibody modalities and engineered formats, including multi-chain constructs.
Create configurable validation and reporting logic that balances scientific rigor with customer flexibility.
Build robust pipelines that convert raw experimental exports and metadata into structured, versioned, analysis-ready datasets.
Implement quantitative analysis and analysis logic for high-throughput characterization data.
Partner with assay scientists and QC stakeholders to define controls, acceptance criteria, and failure modes, then translate them into automated checks and consistent reporting.
Experience developing and applying AI/ML models for antibody/protein sequences and experimental assay data (for example developability prediction, QC triage, or sequence-to-property modeling) is a strong plus.
Collaborate with Data Science/ML teammates on dataset creation, feature engineering, baselines, benchmarking, and model integration.
Apply statistical learning or lightweight ML methods where they provide clear value (for example anomaly detection, drift detection, QC triage, prioritization, risk scoring), emphasizing reliability, interpretability, and measurable impact.
Build maintainable scientific software in Python and contribute to good engineering hygiene (version control, testing, documentation, reproducibility, and robust error handling).