Single-Cell Genomics Benchmark Designer

Obsidian; Greater London; Hybrid; GBP 45,000 - 64,000; Full time

Job summary

Obsidian is seeking a Bioinformatics & Computational Single-Cell Genomics Expert to design graduate-level problems within real workflows, using state-of-the-art scientific software. You’ll create challenging tasks requiring multi-step analyses, plan experiments, and guide AI models to reveal insights from data.

Strong Python and Linux skills are essential, with 15–20 hours weekly commitment. Experience with scanpy, scvelo, squidpy, gudhi is preferred, and candidates should demonstrate

Qualifications

• Graduate-level training in a STEM field (MS/PhD preferred).
• Proven proficiency with at least one of the listed scientific software libraries, demonstrated via publications, open-source work, or professional projects.
• Strong Python skills — writing problem setups, oracle functions, and validators.
• Ability to work independently and refine problem designs based on feedback.
• Comfortable in Linux/terminal environments with remote compute sandboxes.
• Available for 15–20 hours per week.

Responsibilities

• Create graduate-level problems based on real scientific workflows.
• Design problems requiring multi-step analyses and strategic questioning.
• Test problems against state-of-the-art AI models and refine for target difficulty.
• Collaborate with the team to ensure reproducibility and robust evaluation.

Skills

Python

Puzzle design

Independent work

Linux

Education

MS or PhD in STEM

Tools

scanpy

scvelo

squidpy

gudhi

Job description

Obsidian is seeking a Bioinformatics & Computational Single-Cell Genomics Expert to design graduate-level problems within real workflows, using state-of-the-art scientific software. You’ll create challenging tasks requiring multi-step analyses, plan experiments, and guide AI models to reveal insights from data.

Strong Python and Linux skills are essential, with 15–20 hours weekly commitment. Experience with scanpy, scvelo, squidpy, gudhi is preferred, and candidates should demonstrate