Principal Scientist, Bioinformatics

Legend Biotech US•Somerset, NJ

3h•$146,410 - $192,164•Onsite

About The Position

Legend Biotech is seeking a Principal Scientist of Bioinformatics to join its Research & Development team in Somerset, New Jersey. The role focuses on applying AI to drug discovery and protein engineering for cell-based therapies. The scientist will develop generative AI models and agentic AI systems to identify novel disease targets, and apply geometric deep learning and structural biology to design and refine high-affinity binders, such as scFvs, VHHs, and novel scaffolds, for CAR-T cell therapies.

Requirements

Ph.D. in Computational Biology, Computer Science, Structural Biology, or Biophysics.
At least 3 years of post-Ph.D. experience, or at least 6 years with an M.S. or B.S., in the biotech or pharmaceutical industry or an advanced research setting focused on computational drug discovery, target identification, and antibody or binder design.
Expert programming proficiency in Python and deep learning frameworks, primarily PyTorch.
Experience building generative AI models and agentic AI systems using LLM orchestration frameworks to query biomedical databases and literature.
Deep familiarity with structural biology software, including AlphaFold, ESMFold, RFdiffusion, ProteinMPNN, BindCraft, and FoldFlow.
Proficiency with physics-based simulation and structural optimization or visualization tools, such as GROMACS, AMBER, OpenMM, and PyMOL.
Solid understanding of structural immunology.
Expertise in interface biophysics, including calculating interface binding energies (ΔΔG) and evaluating electrostatic surface potentials.
Familiarity with foundational multi-omics platform datasets and target evaluation databases, such as TCGA, Open Targets, Human Protein Atlas, and DepMap.

Responsibilities

Architect and deploy agentic AI systems to search multi-omic datasets, clinical literature, and biological pathways for novel tumor-specific drug targets.
Build predictive frameworks using transcriptomics and other datasets to assess target druggability and potential off-tumor toxicity.
Develop or adapt generative models, including protein language models, diffusion models, and inverse-folding algorithms, to design novel, highly specific binders for tumor antigens.
Use geometric deep learning to model immune interfaces and predict paratope-epitope interactions, aiming for high specificity and reduced off-tumor toxicity.
Review AI-designed binders and address physical anomalies, optimize hydrophobic packing and hydrogen-bond networks, and resolve steric clashes or backbone strain.
Tune binder biophysical properties to support optimal CAR-T signaling and help prevent T-cell exhaustion.

Benefits

Medical, dental, and vision insurance.
401(k) retirement plan with a company match that vests fully on day one.
Eight weeks of paid parental leave after three months of employment.
Paid time off that includes vacation time, personal time, sick time, floating holidays, and eleven company holidays.
Flexible spending and health savings accounts.
Life and AD&D insurance.
Short- and long-term disability coverage.
Legal assistance.
Supplemental plans, including pet, critical illness, accident, and hospital indemnity insurance.
Voluntary commuter benefits.
Family planning and care resources.
Well-being initiatives.
Peer-to-peer recognition programs.
Performance-based bonus and/or equity for employees in eligible roles.