Bioinformatics Scientist, Machine Learning

SAGA Diagnostics is a personalized cancer diagnostics and disease monitoring company focused on molecular genetic analysis of circulating tumor DNA (ctDNA). The company’s mission is to improve precision cancer medicine, provide more accurate treatment monitoring, and improve patient survival using minimally-invasive liquid biopsy cancer testing services. SAGA’s proprietary tests can help patients, oncologists, and drug developers detect actionable mutations, stratify patient groups, and monitor treatment response, residual disease, and disease recurrence at unprecedented sensitivity and scale.

We are seeking a Bioinformatics Scientist focused on Machine Learning to help advance our efforts toward tracking minimal residual disease (MRD) using next-generation sequencing (NGS) and novel computational approaches. This role offers a unique opportunity to lead the exploration and application of machine learning methods in a rapidly evolving clinical landscape, while contributing to the development of scalable, production ready pipelines.

You’ll bring deep and current machine learning (ML) expertise in genomics, algorithm development, and statistical modeling, and play a key role in driving best practices and evaluating new ML approaches.  With a strong foundation in computational biology and a passion for innovation, you’ll work at the forefront of diagnostic development, pushing the boundaries of how cancer is detected and monitored over time.

Responsibilities

• Apply and adapt machine learning and statistical modeling approaches for biomarker discovery and longitudinal disease tracking.
• Build scalable, production-ready analysis pipelines that meet clinical-grade performance standards.
• Drive the adoption and refinement of machine learning best practices, including model interpretability, uncertainty estimation, and reproducibility.
• Design computational strategies for ultrasensitive variant calling, error suppression, and signal extraction from sequencing data.
• Collaborate cross-functionally with bioinformatics and data scientists, R&D and clinical teams to explore new ML approaches and evaluate their potential impact.
• Actively participate in code and design reviews, with a focus on ML model quality, reproducibility, and integration into production pipelines.

Requirements

• Ph.D. in Computational Biology, Bioinformatics, Computer Science, Statistics, or related field.
• At least 2-3 years of postdoctoral or industry experience preferred, with demonstrated contributions in NGS data analysis and algorithm development.
• Strong foundation in machine learning, including GLMs, tree-based methods, and neural networks.
• Experience working with biological datasets, especially DNA sequencing and liquid biopsy.
• Familiarity with ML frameworks (TensorFlow, PyTorch, scikit-learn) for biological data.
• Proficient in Python and its scientific computing libraries (e.g., NumPy, Pandas, Scikit-learn)
• Exposure to cloud computing environments (preferably AWS).
• Eagerness to learn and teach new methods and contribute to a collaborative, fast-paced team.

Preferred but Not Required

-       Familiarity with MRD or ctDNA tracking approaches is a plus

-       Prior contributions to open-source bioinformatics or ML tools

-       Knowledge of regulatory documentation and clinical validation processes.

Benefits

Benefits

·       Competitive Compensation and company wide benefits plan

·       Opportunities for career advancement and professional development.

·       A collaborative and innovative work environment dedicated to improving oncology outcomes.

SAGA Diagnostics is an equal opportunity employer, fully committed to achieving a diverse and inclusive workplace that embraces and encourages applicants of every background.  The company’s policy regarding equal employment opportunity means that all decisions regarding recruitment, hiring, benefits, wage and salary administration, scheduling, disciplinary action and termination will be made without unlawful discrimination on the basis of sex, gender, race, color, age, national origin, religion, disability, medical condition, genetic information, marital status, sexual