Scientific Project Lead — Genomics (AI Evaluation & RL Environments)

About Lumos

Lumos is a health and life-science AI evaluation company based in San Francisco. Our mission is to make health and life-science AI genuinely accurate and safe. We build the benchmarks, RL environments, and adversarial testing frameworks that frontier labs rely on to know whether their models can be trusted with science.

We're scaling our Paris team to support new product launches and foundational lab partnerships — startup velocity, frontier-model stakes, in one of the most beautiful cities in the world.

The Role

You'll be a Scientific Project Lead - the expert at the center of how Lumos builds and evaluates scientific AI. This is a hands-on, production-oriented role, and mission-critical role to help us ensure highest quality data possible. The core of the work is:

• Building gold-standard samples — the expert-annotated tasks and reference solutions that become training and evaluation data for frontier models
• Reviewing and adjudicating the work of a network of domain experts, and owning the quality bar everyone works to
• Designing and shipping RL environments alongside our research and engineering team — the worlds that test whether models actually understand genetics

You'll set quality criteria, break models where they're weak, and be the credible scientific voice in front of customers and our expert network. As Lumos stands up a Paris wet lab, you'll help shape and run it.

What You Will Do

• Build gold-standard, expert-annotated samples and reference solutions across genomics tasks — variant interpretation, differential expression analysis, CRISPR / gene-editing design and off-target assessment, statistical analysis — that become training and eval data for frontier models.
• Review, adjudicate, and quality-grade submissions from a network of domain experts; define, document, and maintain the rubrics and acceptance criteria everyone works to.
• Partner with research and engineering to design and ship RL environments — specifying tasks, tools, verifiers, and acceptance criteria, then iterating as models improve.
• Adversarially test and red-team genomics model submissions to find where they break.
• Act as the genomics subject-matter expert in customer and expert conversations.
• Help stand up and run a Paris wet lab — protocol and assay setup, plus validation studies that ground our digital tasks in real bench data.
• Contribute scientific framing to public benchmark launches and stay active in the field.

What We Are Looking For

• PhD in genetics, genomics, computational biology, or a closely related field.
• 2+ years of post-PhD research or industry experience (postdoc, staff scientist, biotech, or equivalent). This is a senior role — we're optimizing for depth and judgment.
• Hands-on experience across genomics workflows: NGS data analysis (RNA-seq, variant calling), variant interpretation, and/or CRISPR design and off-target assessm
• ent.Strong computational and data-analysis skills — Python or R, plus standard bioinformatics tooling (e.g. DESeq2/edgeR, GATK, Ensembl/VEP).
• Hands-on wet-lab experience in molecular biology / genomics techniques.
• A track record of rigorous, first-author published work in peer-reviewed journals.
• Intellectual rigor, adversarial instinct, and the ability to communicate across research and commercial audiences.
• Strong written and spoken English.

Bonus

• Experience designing or grading benchmarks / evaluations for scientific or ML models.
• Familiarity with public life-science AI benchmarks.
• Prior experience building or annotating ML training data.

Compensation

• €75,000–90,000 basesalary
• Annual performance bonus
• 10k-30k options

Work Authorization

Candidates must be authorized to work in the European Union without sponsorship. Lumos does not sponsor work authorization for this tole.

Start date: Monday, July 27, 2026 (flexible)

Equal Opportunity

Lumos is an equal opportunity employer. We are committed to building a diverse and inclusive team and do not discriminate on the basis of race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or any other characteristic protected by applicable law. All qualified applicants will receive consideration for employment.