Staff Machine Learning Scientist, Oncology Foundation Model

Tempus AI • New York, NY

Not Applicable Posted March 30, 2026 2 variants Job link

Responsibilities

On the LMM architecture team at Tempus AI, you’ll design and define multimodal model architectures, including fusion strategies and modality-specific processing, and implement, refine, benchmark, and optimize them using deep learning frameworks such as PyTorch or TensorFlow. You’ll build and manage end-to-end and distributed training pipelines across cloud GPU fleets for large-scale datasets and models, monitoring, debugging, and resolving performance bottlenecks. You’ll also design and experiment with methods to fuse knowledge into multimodal representations to improve understanding and reasoning, collaborating closely with the knowledge integration engineer to support knowledge injection mechanisms.

Commitments

Tempus AI notes that, for certain remote roles in unincorporated Los Angeles, some criminal history may be considered directly related to key job duties such as customer interaction and handling confidential information, which could affect conditional offers. Qualified applicants with arrest or conviction records will still be considered in accordance with applicable laws, including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act.

Not Met Priorities

What still needs stronger evidence

Requirements

Deep understanding of deep learning principles and architectures (especially transformers).
Extensive experience with multimodal machine learning concepts and techniques (for example, different fusion methods for text and images).
Solid understanding of optimization techniques for large-scale models.
Strong proficiency in Python and deep learning frameworks (PyTorch/TensorFlow) and model management libraries like HF Transformers.
Experience with training large multimodal models with distributed training frameworks (for example, Horovod, MosaicML) and GPU fleet management.
Strong understanding of knowledge representation concepts (for example, knowledge graphs, ontologies).
Experience with distributed training frameworks and cloud computing platforms (for example, GCP, Azure).

Preferred Skills

Experience with distributed training frameworks and cloud computing platforms (for example, GCP, Azure).

Passionate about precision medicine and advancing the healthcare industry?
Recent advancements in underlying technology have finally made it possible for AI to impact clinical care in a meaningful way. Tempus' proprietary platform connects an entire ecosystem of real-world evidence to deliver real-time, actionable insights to physicians, providing critical information about the right treatments for the right patients, at the right time.
Focus: Contribute to the design of the core architecture of LMMs and building of the infrastructure for training it at scale.
Responsibilities: You will contribute to the following activities:

Design and definition of the architecture of the LMMs, considering different fusion strategies and modality-specific processing.
Implement, refine, benchmark and optimize model architectures using deep learning frameworks such as PyTorch or TensorFlow.
Develop and manage the end-to-end training pipelines, including data loading, preprocessing, and model training. Architect and deploy distributed training workflows, optimizing for performance across cloud GPU fleets.
Implement distributed training strategies to handle large-scale datasets and models.
Design and implement methods to fuse knowledge with the multimodal representations within the LMM.
Experiment with different approaches to enhance the model's understanding and reasoning abilities through knowledge integration.
Monitor and debug training processes, identifying and resolving performance bottlenecks.
Collaborate with the knowledge integration engineer to ensure the architecture can accommodate knowledge injection mechanisms.
Skills Needed

Deep understanding of deep learning principles and architectures (especially transformers).
Extensive experience with multimodal machine learning concepts and techniques (for example, different fusion methods for text and images). Solid understanding of optimization techniques for large-scale models.
Strong proficiency in Python and deep learning frameworks (PyTorch/TensorFlow) and model management libraries like HF Transformers.
Experience with training large multimodal models with distributed training frameworks (for example, Horovod, MosaicML) and GPU fleet management.
Strong understanding of knowledge representation concepts (for example, knowledge graphs, ontologies).
Experience with distributed training frameworks and cloud computing platforms (for example, GCP, Azure).
New York Pay Range - $220,000 - $260,000 USD
California Pay Range - $220,000 - $260,000 USD
Illinois Pay Range - $200,000 - $240,000 USD
Remote - USA Range - $200,000 - $240,000 USD
The expected salary range above is applicable if the role is performed from California and may vary for other locations (Colorado, Illinois, New York). Actual salary may vary based on qualifications and experience. Tempus offers a full range of benefits, which may include incentive compensation, restricted stock units, medical and other benefits depending on the position.
Additionally, for remote roles open to individuals in unincorporated Los Angeles – including remote roles- Tempus reasonably believes that criminal history may have a direct, adverse and negative relationship on the following job duties, potentially resulting in the withdrawal of the conditional offer of employment: engaging positively with customers and other employees; accessing confidential information, including intellectual property, trade secrets, and protected health information; and appropriately handling such information in accordance with legal and ethical standards. Qualified applicants with arrest or conviction records will be considered for employment in accordance with applicable law, including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act.
We are an equal opportunity employer. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.