Bioinformatics and Computational Single-Cell Genomics Expert

Design graduate-level computational biology challenges that evaluate whether advanced AI systems can perform research-grade work with real scientific software. This role focuses on original, rigorously tested problems in single-cell genomics, from executing multi-step analyses and interpreting outputs to planning efficient experiments or queries that reveal information not directly visible in the data.

• Create computational problems that require skilled use of specialized scientific software, including fully defined workflows with exact answers and open-ended investigation tasks that require strategic reasoning.
• Develop challenges involving simulations, result interpretation, experimental design, and data-driven discovery.
• Design problems using single-cell RNA-seq analysis, trajectory inference, spatial transcriptomics, and topological data analysis workflows.
• Build tasks around cell-type annotation, pseudotime ordering, multi-omic integration, spatially variable gene identification, and persistence-based analysis pipelines.
• Test problems against advanced AI models and refine them until they achieve the intended level of difficulty.
• Write Python-based problem setups, oracle functions, and solution validators.

• Graduate-level training in a relevant STEM field, including an MS, PhD, or equivalent research experience. MS or PhD credentials are preferred.
• Hands-on experience with bioinformatics and single-cell genomics tools such as scanpy, scvelo, squidpy, and gudhi. Experience with other specialized software in this domain will also be considered.
• Demonstrated proficiency with at least one listed scientific software library through research publications, open-source contributions, or professional work.
• Strong Python programming skills and experience applying these libraries to real research problems.
• Understanding of software limitations, edge cases, and how to create challenges that reward careful reasoning rather than surface-level pattern matching or raw computation.
• Ability to work independently, incorporate feedback, and improve problem designs.
• Comfort working in a Linux terminal environment with remote compute sandboxes.

• Experience with multiple listed domains or tools.
• Familiarity with benchmark or evaluation design.
• Experience teaching scientific topics or designing exams and problem sets.
• Experience with computational reproducibility and containerized environments.

• Remote, hourly engagement.
• Availability of at least 15 to 20 hours per week is required.

$70 to $100 per hour.