Bioinformatics Single-Cell Benchmark Designer

Mercor; Greater London; Hybrid; GBP 60,000 - 90,000; Full time

Benefits offered by this job

Flexible hours

Remote compute sandbox access

Job summary

Mercor is seeking a Bioinformatics & Computational Single-Cell Genomics Expert to help design graduate-level problems for benchmarking AI systems. You will work with real scientific workflows, run simulations, interpret results, and design experiments to uncover hidden information from data.

You will use Scanpy, scVelo, Squidpy, and Gudhi to construct challenging tasks around cell-type annotation, pseudotime, spatial transcriptomics, and topological data analysis.

Qualifications

• Graduate-level training in a STEM field (MS, PhD preferred).
• Proven proficiency with at least one listed scientific software libraries, shown through research publications, open-source contributions, or professional work
• Strong Python skills — you'll be writing problem setups, oracle functions, and solution validators
• Ability to work independently and refine problem designs based on feedback
• Comfortable working in a Linux/terminal environment with remote compute sandboxes
• Available for at least 15–20 hours per week

Responsibilities

• Design original graduate-level problems based on real scientific workflows.
• Test problems against state-of-the-art AI models, refine to hit target difficulty.
• Create problems around cell-type annotation, pseudotime ordering, multi-omic integration.
• Involve persistence-based analysis pipelines and topological data analysis techniques.

Skills

Python

Linux

Independent work

Problem design

Education

MS/PhD in a STEM field

Tools

scanpy

scvelo

squidpy

Gudhi

Job description

Mercor is seeking a Bioinformatics & Computational Single-Cell Genomics Expert to help design graduate-level problems for benchmarking AI systems. You will work with real scientific workflows, run simulations, interpret results, and design experiments to uncover hidden information from data.

You will use Scanpy, scVelo, Squidpy, and Gudhi to construct challenging tasks around cell-type annotation, pseudotime, spatial transcriptomics, and topological data analysis.