Senior Scientist, Machine Learning Research

aalphabio; Seattle (WA); Híbrido; USD 164.000 - 206.000; Jornada completa

Descripción de la vacante

A-Alpha Bio, based in Seattle, WA, seeks a Senior Scientist, Machine Learning Research, to transform large-scale protein interaction data into actionable insights and models. You will lead AI/ML projects, including antibody design and affinity prediction, working with wet labs as needed.

You will collaborate across teams to develop novel AI methods, evaluate performance with robust benchmarks, and deliver reproducible results for internal use and external partners.

Formación

• PhD in a quantitative or life sciences field with 4+ years in software development and AI/ML; or a BA/BS with 12+ years of relevant experience.
• Strong experience with deep learning frameworks (PyTorch, JAX) and modern architectures (VAEs, transformers, GNNs).
• Proficiency in data science best practices: data wrangling, training, evaluation, and scalable deployment.
• Excellent communication skills to explain methods and results to both computational and experimental audiences.

Responsabilidades

• Develop AI/ML methods for predicting and engineering protein-protein interactions.
• Design benchmarks to evaluate model performance, uncertainty, and generalization.
• Deliver data packages, model executables, and technical reports on schedule.
• Contribute to codebase and data, documenting methods and guiding teammates.
• Advance AlphaSeq data utility for protein engineering with innovative computational approaches.
• Lead projects and communicate results to internal teams and external partners.

Conocimientos

Deep learning

PyTorch

JAX

Transformers

GNNs

Educación

PhD in quantitative or life sciences

Bachelor's degree in quantitative or life sciences

Descripción del empleo

A-Alpha Bio is a n early-stage, rapidly growing biotechnology platform company headquartered in Seattle, WA. We are focused on building the foundational data layer for AI-driven protein engineering. We provide biopharma companies and model builders with access to ground truth experimental datasets, including affinity and structure, for training, benchmarking and validating AI protein models. In parallel, we apply our data and models directly with select partners to engineer next-generation dual-specific and molecular glue therapeutics, and to discover and optimize differentiated biologics.

A-Alpha Bio is headquartered in Seattle, WA, but remote applicants are welcome to apply. Candidates must reside in the United States.

Starting Salary Range: $164,000 - $206,000 annually

Exemption Status: Exempt

Location Expectations : Remote-Eligible (expected travel to Seattle HQ once per quarter)

Reporting To : Director, Machine Learning Research

Role Description

A-Alpha Bio is seeking a Senior Scientist, Machine Learning Research to turn large-scale protein interaction data into insights and models that advance antibody and protein engineering. The role focuses on developing innovative AI/ML methods that learn from millions of protein-protein interaction data points to predict and engineer protein binding. The Senior Scientist will take a technical lead on challenging AI/ML projects within the ML Research team, including de novo design of antibodies or minibinders as well as models for affinity prediction and developability optimization. The Senior Scientist will work together with other ML Scientists to design and execute experiments (both in silico and in vitro with the help of wet-lab colleagues), support long-term AI/ML research initiatives, and communicate scientific results to the ML Research team and broader company, as well as to external collaborators and partners.

Key Responsibilities

• Develop AI/ML methods. Design and implement novel AI/ML approaches for the prediction and engineering of protein-protein interactions, drawing on experimental measurements, protein sequences, and structural information, and use these approaches to solve challenges in drug discovery and optimization.
• Evaluate rigorously. Design benchmarks and evaluations that assess model performance, uncertainty, and generalization, using appropriate baselines and guarding against data leakage so that conclusions are scientifically defensible and reproducible.
• Deliver results. Generate deliverables (such as data packages, model executables, and technical reports) to a level of quality suitable for use within the company and by external collaborators, in accordance with assigned timelines.
• Contribute code and data. Expertly contribute to the shared company codebase and database, helping teammates understand judgments and decisions, authoring and reviewing merge requests, documenting methods, organizing data, and ensuring that new capabilities and data are effectively rolled out to the rest of the team.
• Advance our scientific capabilities. Apply scientific discipline and critical thinking to propose and analyze experiments, stay current with emerging technologies and trends, and identify and develop innovative computational approaches that increase the value of AlphaSeq data for protein engineering.
• Lead, collaborate, and communicate. Take a technical leadership role on assigned projects interfacing across departments, provide mentorship to colleagues, help write and publish technical blog articles or scientific papers, and represent A-Alpha Bio publicly at conferences and/or in scientific discussions with key collaborators.

Qualifications & Experience

Required

• PhD in a quantitative or life sciences field (biology, chemistry, physics, computer science, etc.) with 4+ years of professional experience in software development and AI/ML, including 2+ years of hands-on experience with AI/ML using biological sequence and/or structure data; or Bachelor's degree in a quantitative or life sciences field with 12+ years of relevant experience, including 6+ years of professional experience in software development and AI/ML; or an equivalent combination of education and experience
• Strong experience with deep learning, spanning modern software frameworks (PyTorch, JAX), model architectures and approaches (variational autoencoders [VAEs], transformers, graph neural networks [GNNs], diffusion, and flow matching), and common protein engineering tasks (protein language models, inverse folding, and protein structure prediction)
• Strong proficiency with data science best practices, including wrangling and transforming data, model training, model selection, cross-validation, and deployment at scale
• Excellent verbal and written communication skills, including the ability to explain methods, findings, and limitations to computational and experimental audiences, as well as to external collaborators and partners

Preferred

• Expertise with cloud computi