Contact: Neisha Camacho/Terra Parsons - teamnt@penfieldsearch.com
No 3rd party candidates
Job Summary:
The AI Computational Biologist will be a key contributor in developing and applying AI models for target discovery, mechanism elucidation, and drug repurposing, while integrating outputs with wet-lab validation and preclinical research.
You’ll collaborate across disciplines — from ML engineers building/working with foundation models to biologists running assays — ensuring that computational insights translate into tangible therapeutic hypotheses.
This role is ideal for someone who combines deep biological expertise with fluency in modern AI architectures, and who’s passionate about leveraging LLMs and GNNs to accelerate translational discovery.
Key Responsibilities:
AI & Computational Modeling
- Design, train, and implement LLM- and GNN-based models to extract biological relationships from multi-modal data (omics, literature, chemistry, clinical).
- Integrate knowledge graphs and structured biomedical databases to support hypothesis generation for novel targets and mechanisms.
- Collaborate with ML teams to fine-tune and evaluate models on domain-specific tasks such as gene–disease association, pathway prediction, and compound efficacy modeling.
Biological Interpretation & Target Discovery
- Apply AI-driven insights to identify, prioritize, and validate new drug targets and therapeutic hypotheses.
- Design in silico analyses to support mechanism-of-action elucidation, biomarker discovery, and patient stratification.
- Collaborate with wet-lab teams to translate computational predictions into experimental designs, ensuring seamless handoff between in silico and in vitro/in vivo validation.
Data Integration & Curation
- Integrate large-scale datasets from public and proprietary sources (e.g., transcriptomics, proteomics, CRISPR screens, literature corpora).
- Curate structured datasets for LLM fine-tuning, knowledge graph expansion, and GNN training.
Collaboration & Cross-Functional Impact
- Partner with drug discovery, data science, and AI engineering teams to align modeling objectives with biological relevance.
- Contribute to multi-disciplinary project teams driving programs from discovery through preclinical proof-of-concept.
- Communicate computational findings clearly to both scientific and non-technical stakeholders.
Education:
PhD or MS with 5+ years of relevant experience in Computational Biology, Bioinformatics, Systems Biology, Computer Science, or a related discipline.
Core Competencies:
- Proven experience in target identification and translational discovery — from in silico analysis to preclinical validation.
- Strong understanding of molecular biology, pharmacology, and disease biology.
- Hands-on experience developing or applying AI/ML models to biological problems, especially LLMs, GNNs, or multi-modal integration architectures.
- Prior involvement in wet-lab collaboration (assay design, data interpretation, or experimental validation) preferred.
Technical Skills:
- Programming: Expert in Python (pandas, PyTorch, TensorFlow, scikit-learn, Hugging Face, PyTorch Geometric).
- AI/ML Expertise: Proficiency in LLMs, GNNs, transformers, and model fine-tuning workflows.
- Bioinformatics Tools: Familiar with databases such as Ensembl, UniProt, ChEMBL, DrugBank, GEO, and OMIM.
- Data Integration: Experience with multi-omics data fusion and biomedical knowledge graphs.
- Visualization & Communication: Skilled in building interpretable visualizations and clearly communicating computational findings.
- Version Control: Proficient in Git and collaborative coding practices.
- Familiarity with molecular modeling, chemoinformatics, or AI for protein–ligand interaction prediction.
- Experience in biomedical NLP, scientific literature mining, or ontology construction.
- Understanding of preclinical pharmacology or toxicogenomics.
- Experience working in cloud environments (GCP, AWS).
Soft Skills:
- Deep curiosity and excitement about connecting AI architectures with biological meaning.
- Excellent cross-disciplinary communication — able to converse equally well with AI engineers and biologists.
- Self-directed, detail-oriented, and comfortable working in a fast-paced, dynamic startup environment.
- Passionate about improving patient outcomes through innovative science and technology.
