Senior/Principal Scientist – AI/ML Protein & Antibody Drug Discovery

Responsibilities

• Machine Learning Model Development

• Design and fine-tune deep learning and LLM-based models (e.g., LLaMA 3.3, DiffDock, ProteinMPNN) for sequence–structure–activity prediction and optimization.
• Integrate antibody and protein-specific biological knowledge into model architectures and training strategies.

• Antibody and Protein Therapeutic Design

• Apply ML to support antibody humanization, CDR optimization, stability prediction, developability filtering, and manufacturability assessment.
• Collaborate with discovery teams to deploy AI-driven workflows across antibody, multi-specific, and cyclic peptide programs.

• Data Integration & Pipeline Ownership

• Build robust pipelines for aggregating and structuring internal R&D data (sequences, 3D structures, binding data, developability attributes) for ML modeling.
• Develop ETL systems and embedding workflows using LangChain, Milvus, or MariaDB Vector DB to support RAG-based knowledge retrieval and protein annotation.

• Scientific and Cross-Functional Leadership

• Serve as the AI/ML technical lead on discovery programs, interfacing with computational biology, protein engineering, immunology, and bioinformatics teams.
• Mentor junior team members, guide experimental design informed by ML models, and ensure reproducibility and traceability for downstream applications.

• Computing & Productionization

• Scale model training and inference across GPU/HPC environments using frameworks like Dask, Ray, MPI, or AWS.
• Ensure models and pipelines are integrated into scientific production environments (LIMS, R&D cloud platforms, etc.).

Requirements

• Ph.D. in Computational Biology, Computer Science, Bioinformatics, Structural Biology, or a related field
• 5+ years of experience in AI/ML applied to protein or antibody drug discovery in an industry or translational research setting
• Proven track record of developing and applying ML models for antibody/protein optimization, structure-function modeling, or drug design
• Proficient in Python and deep learning frameworks such as PyTorch or TensorFlow
• Experience with LLMs, GNNs, and relevant tools for structure and sequence analysis (e.g., AlphaFold, Rosetta, DiffDock)
• Strong understanding of antibody engineering principles, therapeutic design challenges, and developability constraints
• Demonstrated ability to work across disciplines and communicate complex ideas to cross-functional teams

Preferred Qualifications

• Experience building or leading AI/ML workflows embedded in therapeutic discovery pipelines
• Familiarity with AI-guided antibody design, cyclic peptides, or novel protein modalities
• Prior exposure to IND or regulatory-facing AI/data packages
• Publication or speaking track record in ML for drug discovery or structural biology

Who This Role Is Not For

• This is not a general AI/ML engineering role. Candidates without prior experience applying machine learning to therapeutic discovery, protein modeling, or antibody design will not be considered.
• We are specifically seeking scientists who have applied computational models in the biopharma or drug discovery setting, not those coming solely from academic ML, generic NLP, or unrelated AI fields.