Machine Learning Engineer (Contract)

Overview

Seeking a Machine Learning Bioinformatics Engineer to develop and deploy advanced ML solutions supporting pharmaceutical R&D. This role focuses on analyzing large-scale, multimodal clinicogenomic datasets (genomic, transcriptomic, clinical, and real-world data) to drive insights into disease biology, patient stratification, and treatment response. Ideal candidates are strong in both machine learning and bioinformatics, with a passion for translating complex data into impactful discoveries.

Key Responsibilities

• Build and deploy scalable, production-ready machine learning models
• Process and analyze genomic and transcriptomic data using bioinformatics pipelines
• Prepare high-quality, normalized biological datasets for downstream analysis
• Train large-scale models using frameworks like PyTorch Lightning and Hugging Face
• Develop cloud-based ML solutions (AWS/GCP) with a focus on scalability and reproducibility
• Collaborate with cross-functional teams to uncover biomarkers and therapeutic targets
• Provide technical input and guidance on ML system design and implementation

Qualifications

• PhD with 0-2 years of relevant work experience, or MS with 3-5 years of relevant work experience, or BS with 4-7 years of relevant work experience.
• Proficient programming skills: Strong Python programming skills with extensive experience in ML and data libraries (e.g., NumPy, pandas, PyTorch).
• Deep ML expertise: Excellent knowledge of modern machine learning methods and development best practices, including training strategies, model validation, performance visualization, and experimental design.
• Deep bioinformatic expertise: Proficient knowledge of bioinformatic processing pipelines for genomic and transcriptomic variables.
• Strong knowledge of computational oncology, cancer genomics and analysis of clinicogenomics datasets.
• Must be authorized to work in the United States