Machine Learning Application Engineer II

Maze Therapeutics•South San Francisco, CA

11h•Hybrid

About The Position

At Maze Therapeutics, we believe precision medicine has the power to transform the lives of patients with both common and rare diseases. As a Machine Learning Engineer, you will play a hands‑on role in delivering high‑impact, production‑grade solutions that advance our drug discovery programs. You will design, build, and scale data and machine learning infrastructure across early research, lead optimization, and development stages of the drug discovery pipeline. In this role, you will enable data‑driven science while upholding strong engineering standards and FAIR data principles. This position reports to a Senior Data Engineer.

Requirements

Master’s degree in Computer Science, Machine Learning, Bioinformatics, Data Engineering, or related fields.
3+ years of industry experience building production-grade data and ML pipelines, preferably in life sciences supporting drug discovery.
Hands-on experience deploying AI/ML models in drug discovery applications (e.g., computational biology/chemistry workflows).
Experience with FAIR data principles and strong programming skills in Python and SQL (R is a plus).
Proven experience in deploying and maintaining ML systems, including CI/CD, workflow orchestration, and monitoring.
Experience with workflow orchestration tools (e.g., Airflow, Prefect).
Experience with containerization and cloud infrastructure (Docker, Kubernetes, AWS or similar).

Responsibilities

Support management of biobank scale datasets in Polaris, Maze’s internal platform supporting Compass, by building scalable data ingestion, cleaning, processing, and validation pipelines.
Work with scientific compute teams to design and deploy machine learning models to support workflows in research and small molecule drug discovery (compound property prediction, assay data prediction, data analysis).
Lead the evaluation and integration of Large Language Models (LLMs) to automate data ingestion workflows, enhance intelligent querying, and support user-facing variant association and scientific visualization platforms.
Design and operate scalable ML and data platforms leveraging Terraform (IaC) and Git-based CI/CD pipelines, incorporating workflow orchestration, automated model lifecycle management, and production-grade monitoring and reliability.
Collaborate with development organization to evaluate and deploy ML tools that support workflows across Regulatory, Clinical Operations, and Medical Affairs.
Collaborate cross-functionally translate scientific requirements into production-grade systems.