Role Overview:
We are seeking Bioinformatics and Computational Genomics experts to design challenging, agentic genomics tasks and reference solutions for GeneBench Pro. You will create realistic computational biology problems that require an AI agent to interpret biological data, write and execute code, work across scientific files, and produce objectively verifiable outputs. Tasks should reflect authentic genomics and bioinformatics workflows rather than standalone biology questions.
Environment:
Each GeneBench Pro problem is a self-contained scientific analysis. Agents receive an isolated workspace with a short prompt, data files, and a standard bioinformatics stack including Python, scientific computing libraries, and basic genomics packages such as PLINK 2.0. Reference solutions must run in this Python-based environment.
Key Responsibilities:
- Design novel, model-challenging tasks in computational genomics and bioinformatics.
- Design tasks that test higher-order scientific judgment, including handling ambiguous or messy data, identifying artifacts, selecting appropriate analytical approaches, revising assumptions based on intermediate results, and determining when conclusions are decision-ready.
- Build tasks involving realistic scientific data such as FASTA/FASTQ, VCF, BAM/SAM, BED, TSV/CSV, sequence annotations, expression data, germline or somatic variant data, or other genomics artifacts.
- Develop tasks requiring multi-step analysis using Python, command-line tools, or established bioinformatics libraries.
- Create clear task specifications, input datasets, expected output schemas, and deterministic or objectively verifiable ground truths.
- Develop expert reference solutions and reproducible computational workflows that run in the provided Python stack.
- Validate that tasks are scientifically correct, solvable from the supplied information, and sufficiently challenging for frontier AI models.
- Design robust grading criteria that distinguish scientifically correct solutions from superficially plausible outputs.
- Ensure all deliverables are well documented, reproducible, and client-ready.
- Maintain high quality and throughput while incorporating reviewer feedback.
- Communicate progress, blockers, and scientific or technical requirements to project leads and reviewers.
Qualifications Required:
- Ph.D., postdoctoral experience, or equivalent research experience in Bioinformatics, Computational Biology, Genomics, Computational Genetics, or a closely related discipline.
- Strong hands-on programming experience in Python.
- Experience analyzing biological sequence or genomics datasets.
- Comfortable working in Linux/command-line computational environments.
Preferred:
- Experience with genomics workflows such as variant analysis, transcriptomics, sequence analysis, phylogenetics, population genetics, functional genomics, or clinical genomics.
- Familiarity with common bioinformatics libraries and tools such as Biopython, pandas, NumPy, SciPy, samtools, bcftools, BLAST, PLINK, or equivalent tools.
- Experience developing reproducible scientific pipelines.
- Experience evaluating AI/LLM systems on computational scientific tasks.
- Strong understanding of experimental and biological context behind computational analyses.
Bonus Points For:
- Experience with AI agents or coding agents.
- Experience designing benchmark datasets or automated graders.
- Publications involving computational genomics or bioinformatics.
- Experience with Docker/containerized scientific workflows.
Offer Details:
- Commitments Required : Overlap of 4 hours with PST and 40 hrs/week
- Engagement type : Contractor assignment/freelancer (no medical/paid leave)
- Duration of contract : 6 weeks
