Machine Learning Research Scientist
Job Description: Machine Learning Scientist - Computational Biologics Discovery
We are working with a cutting-edge biomedicines company at the intersection of machine learning, protein engineering, and immunology. This innovative team is building a frontier AI platform to accelerate the computational discovery and optimization of next-generation biologic drugs. Backed by top investors and driven by a superstar group of ML scientists, structural biologists, and immunologists, our client is on a mission to translate audacious ideas into breakthrough therapies for immune-mediated diseases.
Position: Machine Learning Scientist - Computational Biologics Discovery
Location: On-site
Type: Full-Time
What You'll Do
Model Innovation: Design and train novel ML models that optimize natural proteins for therapeutic properties and engineer entirely new classes of synthetic proteins with targeted functions.
De Novo Antibody Design: Lead computational antibody design efforts to generate high-affinity candidates against challenging antigens.
Data Integration: Fuse diverse data sources-protein sequence, structure, functional assays, and molecular characterization-to drive multi-objective optimization of protein drug candidates.
Cross-Functional Collaboration: Partner with wet-lab scientists, immunologists, and clinical experts to iteratively refine in-silico designs and accelerate their translation into experimental validation.
Infrastructure & Deployment: Establish and maintain robust data infrastructure and production-quality codebases for model training, deployment, and interactive visualization tools.
Communication & Reporting: Present scientific progress in regular team meetings and prepare clear, compelling reports and slide decks for internal and external stakeholders.
Who You Are
Scientific & Technical Expertise: PhD in Computational Biology, Computer Science, Statistics, or a related field-or equivalent computational experience. Deep knowledge of protein biochemistry, molecular biology, and ML theory.
Proven Track Record: 3+ years of industry experience applying deep learning (e.g., variational autoencoders, graph neural networks) to protein engineering, drug discovery, or related domains.
Hands-On Protein Design: Experience with sequence- and structure-based generative models (e.g., LLMs for sequences, diffusion/inverse-folding models) and familiarity with real-world lab workflows.
Collaboration & Communication: Demonstrated ability to bridge dry-lab and wet-lab teams, translating complex ML outputs into actionable experimental plans and conveying results to diverse audiences.
Entrepreneurial Mindset: Self-driven, adaptable, and comfortable working with high-level objectives in a fast-paced startup environment.
Nice to Have
Experience with cloud computing (AWS, GCP) and containerization (Docker).
Familiarity with interactive app frameworks (Dash, R Shiny).
Prior work in immunology or genomics, with publications in relevant journals.
What They Offer
High Impact: Directly contribute to a platform that speeds the creation of novel biologic drugs and improves patient outcomes.
Collaborative Culture: Join a supportive, interdisciplinary team that values creativity, scientific rigor, and patient-centric innovation.
Competitive Package: Attractive salary, equity, and comprehensive benefits.
Career Growth: Opportunities for leadership, mentorship, and professional development in a rapidly growing startup.
Mission-Driven Environment: Work every day toward delivering breakthrough therapies for immune-system diseases.