Senior AI Research Engineer

About QuantHealth

QuantHealth is a fast-growing AI company transforming drug development through clinical simulations, predictions of disease progression and treatment effects, and large-scale biomedical AI.

Our platform combines real-world patient data from over 350 million patients, biomedical knowledge graphs, and advanced machine learning models to simulate clinical trials and predict

patient outcomes. Pharmaceutical companies use QuantHealth platform to optimize trial design, reduce development risk, and accelerate the development of new therapies.

At the core of our platform is a family of proprietary AI models that learn from large-scale longitudinal healthcare data and biomedical knowledge to model disease progression, treatment effects, and clinical trial outcomes.

About the Role

We are looking for a Senior AI Research Engineer to help develop the next generation of QuantHealth’s core AI technology.

This is a highly technical, hands-on role focused on advancing our foundation models and predictive modeling capabilities. You will work closely with the Director of AI & Algorithms

and a team of researchers and engineers to develop novel machine learning approaches that improve how clinical outcomes, treatment effects, and patient trajectories are modeled.

The ideal candidate combines strong research instincts with exceptional implementation skills. You are comfortable reading and evaluating cutting-edge research, designing new modeling

approaches, and turning ideas into robust, production-ready systems. This role is primarily an individual contributor position, with a strong emphasis on research,

experimentation, algorithm development, and technical execution.

Responsibilities

• Design, develop, and evaluate novel machine learning algorithms that advance QuantHealth’s core modeling capabilities.
• Drive the development of significant components of the next generation of QuantHealth foundation models and predictive modeling systems.
• Evaluate, implement, and extend state-of-the-art machine learning research and translate promising advances into QuantHealth’s modeling platform.
• Research and implement state-of-the-art approaches in areas such as:

1. Transformer architectures
2. Self-supervised and representation learning
3. Foundation models
4. Multimodal learning
5. Knowledge-graph-enhanced modeling
6. Temporal modeling of longitudinal patient data
7. Causal and treatment-effect modeling
8. Uncertainty quantification

• Design and evaluate new pre-training objectives, model architectures, representations, and learning strategies.
• Develop rigorous validation methodologies and contribute to benchmarking and evaluation frameworks.
• Implement research ideas efficiently and at high-quality using modern machine learning frameworks.
• Collaborate closely with Clinical Teams, DataOps, MLOps, Product, and Engineering teams.
• Stay current with advances in machine learning and identify opportunities to incorporate relevant innovations into QuantHealth’s platform.
• Communicate technical findings clearly and proactively raise risks, limitations, and opportunities when identified.
• Contribute to scientific publications, patents, and external thought leadership initiatives when appropriate.

Qualifications

• MSc or PhD in Computer Science, Machine Learning, Statistics, Mathematics, Physics, Computational Biology, or a related quantitative discipline. PhD strongly preferred.
• 5+ years of experience developing advanced machine learning systems in industry, academia, or both.
• Strong hands-on experience developing deep learning systems using PyTorch or equivalent frameworks.
• Demonstrated experience designing, implementing, and evaluating novel machine learning approaches.
• Deep expertise in modern machine learning architectures, including transformer-based models, self-supervised learning, representation learning, and foundation models.
• Experience designing, training, adapting, and optimizing transformer-based and other large-scale machine learning models, including distributed training and large-scale
• experimentation environments.
• Strong background in machine learning, statistics, optimization, and experimental design.
• Experience translating research concepts into reliable software and production-ready systems.
• Excellent software engineering skills and coding practices.
• Strong communication skills and ability to work effectively in highly cross-functional environments.
• Proven ability to work independently, drive complex projects, and operate with high ownership.
• Proven ability to critically evaluate scientific literature and independently identify promising research directions.

Strong Advantages

• Experience developing foundation models, large language models, or large-scale self- supervised learning systems.
• Experience with multimodal machine learning.
• Experience with graph neural networks, knowledge graphs, or representation learning over-structured biomedical data.
• Experience with causal inference, treatment-effect estimation, survival analysis, or time-to-event modeling.
• Experience working with healthcare, biomedical, pharmaceutical, or real-world patient data.
• Track record of publications at leading machine learning or AI conferences.
• Experience working in high-growth startup environments.
• Experience implementing and extending state-of-the-art research papers.