This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Staff Machine Learning Scientist, Translational AI based in the United States.
This role sits at the intersection of advanced deep learning and translational medicine, focusing on turning large-scale genomic, transcriptomic, and multimodal biological data into clinically meaningful insights. You will lead the design and validation of foundation and representation learning models applied to oncology, molecular diagnostics, and patient stratification. The work involves bridging research-grade AI with real-world clinical utility, ensuring models are not only high-performing but also biologically grounded and clinically valid. You will operate with significant autonomy, shaping modeling strategy across multiple initiatives while collaborating closely with computational biology, clinical science, and AI research teams. This is a highly impactful role where your work directly contributes to improving diagnostic accuracy and therapeutic decision-making in healthcare. You will also play a key role in advancing scientific rigor, reproducibility, and translational impact across AI-driven biomedical systems.
Accountabilities:
In this role, you will lead the development and translation of advanced machine learning models into clinically validated tools that support oncology research, diagnostics, and therapeutic decision-making.
- Lead the design, training, and evaluation of foundation models for genomic, transcriptomic, and multimodal biological data in oncology and translational medicine.
- Develop post-training, fine-tuning, and parameter-efficient adaptation workflows to align large models with real-world clinical and molecular datasets.
- Design rigorous validation frameworks that connect model outputs to biological signals, clinical outcomes, and real-world evidence.
- Build and optimize deep learning systems for tasks such as biomarker discovery, recurrence monitoring, and treatment response prediction.
- Identify and mitigate dataset bias, covariate shift, and model failure modes in clinically sensitive AI pipelines.
- Translate complex biological and clinical requirements into structured machine learning problems and scalable model architectures.
- Collaborate across AI Research, Computational Biology, and Clinical Science teams to ensure reproducibility and translational validity of models.
- Contribute to scientific communication through technical documentation, publications, and presentations in academic and industry forums.
Requirements:
This role requires a highly experienced machine learning scientist with deep expertise in foundation models, biological data, and translational AI applications.
- PhD in Computer Science, Computational Biology, Bioinformatics, Biomedical Engineering, or a closely related quantitative field.
- 5+ years of experience applying deep learning to genomic, clinical, or multi-omic datasets, ideally in oncology or immunology contexts.
- Strong expertise in transformer architectures, representation learning, self-supervised learning, and sequence modeling.
- Proven ability to translate ML model outputs into clinically or biologically meaningful insights, not just offline metrics.
- Advanced proficiency in PyTorch and modern ML ecosystems such as Hugging Face, PEFT frameworks, and distributed training systems.
- Experience leading end-to-end model development, including architecture design, experimentation, and deployment readiness.
- Strong understanding of experimental design, statistical validation, and model evaluation in high-stakes environments.
- Excellent communication skills with the ability to bridge technical, biological, and clinical stakeholders.
Benefits:
- Competitive compensation aligned with experience and expertise (remote US-based role).
- Fully remote work flexibility across the United States.
- Comprehensive medical, dental, vision, and disability coverage.
- Paid parental leave and family support programs.
- Retirement savings plan (401k) with employer contributions.
- Equity opportunities and long-term incentive programs.
- Access to cutting-edge AI research, high-performance computing, and cloud infrastructure.
- Professional development support and opportunities for scientific publishing and conference participation.