Bioinformatics & Computational Single-Cell Genomics Expert

Design graduate-level computational genomics challenges that evaluate whether advanced AI systems can perform research-grade scientific work with real software. This role focuses on creating original problems that require AI systems to run analyses, interpret results, design experiments, and uncover information from complex biological data.

Role Overview

You will develop and test rigorous computational problems based on authentic scientific workflows. Problems may require exact, multi-step analyses from fully specified inputs, or strategic planning of queries and experiments to reveal information that is not directly observable. You will test each problem with advanced AI models and refine it to achieve the intended level of difficulty.

Key Responsibilities

• Create original computational problems that require skilled use of specialized scientific software.
• Develop tasks involving simulations, result interpretation, experimental design, and data-driven discovery.
• Design challenges where candidates must determine what to measure, interpret partial outputs, and efficiently narrow possible conclusions.
• Build problems that reward careful reasoning rather than surface-level pattern matching or raw computation alone.
• Test problem designs against advanced AI models and iterate based on results and feedback.
• Write problem setups, oracle functions, and solution validators in Python.

Qualifications

• Graduate-level training in a relevant STEM field, including an MS, PhD, or equivalent research experience. An MS or PhD is preferred.
• Hands-on bioinformatics and single-cell genomics experience, including research use of specialized software rather than theoretical familiarity alone.
• Proficiency with at least one listed scientific software library, demonstrated through research publications, open-source contributions, or professional work.
• Strong Python programming skills.
• Ability to work independently and improve problem designs in response to feedback.
• Comfort working in a Linux terminal environment with remote compute sandboxes.
• Understanding of software limitations, edge cases, and what makes a scientific problem genuinely challenging.

Domain Expertise

This role prioritizes expertise in single-cell RNA-seq analysis, trajectory inference, spatial transcriptomics, and topological data analysis. Relevant tools include scanpy, scvelo, squidpy, and gudhi, along with other specialized software used in this domain.

• Design problems involving cell-type annotation, pseudotime ordering, multi-omic integration, spatially variable gene identification, and persistence-based analysis pipelines.
• Experience with other specialized bioinformatics and single-cell genomics tools will also be considered.

Preferred Experience

• Experience across multiple relevant tools or scientific domains.
• Familiarity with benchmark or evaluation design.
• Scientific teaching, exam design, or problem-set development experience.
• Experience with computational reproducibility and containerized environments.

Work Terms

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

Compensation

$70-$100 per hour.