SandboxAQ’s AI Simulation team develops new drugs and materials using a spectrum of AI and physics-based computational solutions. We are seeking an experienced and innovative Bioinformatics / Knowledge Graphs Researcher to amplify our ability to reason causally about biological systems, based on multimodal inputs from a variety of inputs, including simulation. The successful candidate will show strong ability in computational biology, including knowledge of cutting-edge machine learning techniques, particularly involving large graph data structures such as knowledge graphs. They will have experience creating maintainable software (Python) to those ends. These skills will be leveraged within a seasoned, agile, and multi-disciplinary group, including drug hunters with an excellent track record in drug discovery, computational chemists, physicists, AI experts, and software engineers.
Key Responsibilities
- Create and implement software to construct and operate on biomedical knowledge graphs, drawing from simulated, omics, and literature data.
- Contribute to ongoing research towards applications of the above, including for biomarker ID and toxicity prediction.
- Present to and interact with anyone who needs to understand your work, including clients, other scientists, and non-technical team members.
- Write patents, journal articles, and whitepapers. Speak at conferences and in pitch meetings.
- Vastly improve drug discovery and development on a social scale. Help make better drugs, and help make the tools to do so.
- Co-create a team that does drug discovery better than any has before. Influence hearts and minds, lead by example, and make the world better.
Basic Qualifications
- PhD in a relevant field (bioinformatics, computational biology or similar).
- At least 4+ years professional experience performing causal reasoning over complex biomedical data, including multi-omics and literature data
- The above should include pharma/biotech experience, and may include postdoctoral experience
- Experience processing omics, simulation, and textual (literature) data, including via novel technologies like LLMs
- Able to build and maintain biomedical knowledge graphs
- Strong machine learning background
- Strong enough Python skills to independently do all of the above in a maintainable way
Preferred Qualifications
- Proven background in physics-based and AI-based molecular simulation
- Knowledge of biomarker ID and toxicity prediction
- Experience in clinical development
- Experience in immunology
- Excellent publication record
- Willingness to travel less than 25% to conferences, offsites, customers, and internal meetings.
The US base salary range for this full-time position is expected to be $150k - $210k per year. Our salary ranges are determined by role and level. Within the range, individual pay is determined by factors including job-related skills, experience, and relevant education or training. This role may be eligible for annual discretionary bonuses and equity.
