Job Description

Senior Scientist, AI/ML Drug Discovery

Stealth-Mode Biotech | SF Bay Area, CA

*title and compensation flexible based on background/pedigree

Our client is a stealth-mode biotech startup pioneering AI-first approaches to drug discovery, integrating deep learning, generative models, and large-scale biological datasets to accelerate the development of first-in-class therapeutics.

Responsibilities

• Design and implement novel generative architectures (e.g., VAEs, GANs, Diffusion Models) for in silico drug design using chemical space representations such as SMILES, SELFIES, and molecular graphs.
• Apply Graph Neural Networks (GNNs) and Transformer-based architectures to learn molecular embeddings, model protein-drug interactions, and predict functional outcomes.
• Leverage multi-omics datasets (RNA-seq, proteomics, single-cell transcriptomics, epigenomics) to extract biologically meaningful insights and integrate them into predictive models.
• Optimize large-scale deep learning pipelines for sequence-based and structure-based drug discovery applications, including protein folding (AlphaFold-inspired), docking simulations, and binding affinity predictions.
• Contribute to the development of scalable, cloud-based ML workflows (AWS/GCP, Kubernetes, Ray) for high-throughput model training and inference.
• Maintain cutting-edge knowledge of AI/ML in drug discovery and integrate best practices into our workflows.

Qualifications

• PhD (or MS with equivalent experience) in Computer Science, Machine Learning, Computational Biology, Bioinformatics, Computational Chemistry, or a related field.
• 3+ years of hands-on experience in applying deep learning to drug discovery, structural biology, cheminformatics, or genomics.
• Proven expertise in deep learning architectures, including Transformers (BERT, ESM, AlphaFold), GNNs (GraphConv, GAT, SchNet, GVP), VAEs, and Diffusion Models.
• Strong background in molecular representation learning, including SMILES embeddings, graph-based molecular descriptors, and structure-based protein-drug modeling.
• Experience with multi-modal AI models that integrate chemical, biological, and clinical datasets for predictive analytics.
• Ability to handle high-throughput biological data processing, including working with sequencing data, expression matrices, and biomarker discovery pipelines.
• Strong software engineering skills in Python, NumPy, Pandas, SQL, and distributed computing (Dask, Ray, Spark).
• Experience deploying scalable AI models in cloud environments (AWS SageMaker, Vertex AI, Kubernetes, Docker).
• A strong publication record in machine learning, computational biology, or AI-driven drug discovery.

Why Join?

• Stealth-mode opportunity – Influence foundational AI-driven drug discovery pipelines before public launch.
• Cutting-edge AI/ML research – Work with top experts in AI and computational biology.
• Massive impact – Accelerate drug development for diseases with high unmet need.
• Equity & Competitive Compensation – Early-stage upside + competitive salary and benefits.
• Career Growth – Leadership opportunities as the company scales.

Job Tags

Similar Jobs