Preferred Qualifications:PhD in computational biology, bioinformatics, immunology, structural biology, biochemistry, or a closely related fieldWorking knowledge of antibody biology: CDR structure, germline gene usage, VH/VL pairing, somatic hypermutation, affinity maturation mechanisms, and antibody-antigen recognitionFamiliarity with B cell biology and the humoral immune response, including germinal center reactions and clonal selection[TYC1] Strong Python programming skills with hands-on experience building and evaluating machine learning models (PyTorch or JAX); ability to write and maintain research-grade softwareExperience with protein structure prediction or molecular modeling tools (AlphaFold2/3, Rosetta, FoldX, OpenMM, or equivalent)Comfort working in a Linux/HPC environment with version control (Git) and reproducible workflow practicesStrong written and oral communication skills - ability to present computational findings clearly to mixed computational and experimental audiencesDemonstrated ability to work independently and drive projects from conception to publicationCollaborative mindset: comfort working at the interface of computational and wet-lab teams, translating model outputs into experimental hypotheses and integrating assay results back into the modeling cycleExperience with machine learning and antibody engineering Hands-on experience with antibody-specific language models - AbLang, AntiBERTy, ESM2/ESM3, IgLM, or equivalent - for sequence design, mutation scoring, or affinity predictionFamiliarity with zero-shot or fine-tuned PLM strategies for predicting the effect of mutations on binding affinity (G estimation, fitness landscape modeling)Experience with deep mutational scanning datasets or related benchmarks (e.g., AbBiBench, ProteinGym) for model evaluationExperience with generative protein design tools - RFdiffusion (including the antibody-fine-tuned variant), ProteinMPNN, RFantibody, or AntiFold - for CDR loop design and sequence optimizationFamiliarity with structure-based filtering and validation pipelines: RoseTTAFold2, ABodyBuilder3, or equivalent antibody structure predictorsExperience designing or evaluating antibody-antigen interfaces computationally, including epitope targeting and paratope modelingExperience with AIRR-seq (BCR repertoire) data analysis: V(D)J annotation, clonal lineage tracing, somatic hypermutation profiling, and CDR3 clusteringFamiliarity with repertoire analysis tools and frameworks: IMGT/ANARCI, Change-O, Immcantation, or airflowExperience mining OAS, SAbDab, or iReceptor for training data construction and antigen-specific clone discoveryKnowledge of antibody developability frameworks: deamidation, oxidation, aggregation hotspot prediction, and humanization strategiesPrior experience with yeast display, phage display, or single B cell sorting in a collaborative wet-lab settingActive learning or Bayesian optimization experience for closed-loop experimental design Minimum Education:Doctoral/Terminal DegreePhysical Requirements:Exerts up to 20 pounds of force occasionally and/or up to 10 pounds frequently and/or a negligible amount constantly to move objects. Key areas of Contribution:Research & ScholarshipConceptualize original research questions at the intersection of machine learning, structural biology, and therapeutic antibody engineeringLead the design and execution of computational research programs, from hypothesis generation through manuscript preparationAuthor and co-author papers targeting high-impact journals in computational biology, structural biology, and chemical biology (e.g., Nature, PNAS, Nature Communications, npj digitial medicine, NeuralIPS)Present findings at national and international conferences, building your independent scientific profileComputational DevelopmentDesign, implement, and benchmark ML pipelines for mutation effect prediction, fitness landscape modeling, and generative antibody design using protein language models (ESM2/ESM3) and structure-based scoringBuild reproducible, version-controlled workflows for AlphaFold2/3, Rosetta/FoldX ddG estimation, and antibody-antigen complex analysisDevelop and maintain shared computational infrastructure and documentation for team-wide useWet-Lab CollaborationWork closely with wet-lab partners to translate computational predictions into experimentally testable hypotheses - design the experiment, not just the modelInterpret SPR, BLI, ELISA, and SEC-HPLC data and feed results back into model retraining and active learning loopsParticipate in joint design-test-learn meetings, co-authoring experimental design documents spanning both teamsTriage antibody candidates for developability liabilities - deamidation, oxidation, aggregation hotspots - in collaboration with the characterization team.