About BostonGene

BostonGene is a precision oncology company focused on translating complex biological and clinical data into actionable insights for drug development and patient stratification. We operate at the intersection of computational biology, multi-omics, immune profiling, and AI, working with biopharma partners and internal product teams to accelerate biomarker discovery, clinical trial enablement, and evidence generation

Position Summary

We are hiring a Senior Bioinformatics Data Analyst in AI/ML Group to contribute to the science and engineering of the TCR/BCR repertoire branch. Working alongside existing workstream leads, you will help build repertoire encoders and benchmark suites that integrate into BostonGene's multimodal foundation model stack. This is a hands-on role focused on model development, data pipelines, and rigorous evaluation, with room to grow into broader technical ownership over time

• Model development: design, train, and iterate on encoders for immune receptor sequences and repertoires (TCR/BCR), including repertoire aggregation modules and patient-level embeddings.
• Data & QC pipelines: build and maintain pipelines for repertoire reconstruction/QC, harmonization across assays/cohorts, and “AI-ready” dataset construction.
• Benchmarking & validation: implement evaluation gates (biological plausibility checks, generalization across cohorts, robustness to coverage/missingness, reproducibility).
• Roadmap contribution: help shape representation targets (sequence-level and repertoire-level), training objectives, and the benchmark suite alongside branch leads.
• Cross-branch collaboration: work with Immune System and multimodal fusion teams to align immune-state representations and support coherent patient-level integration.
• Engineering rigor: follow the branch “definition of done” (docs, tests, training logs, model cards, versioning).