Senior Research Scientist, AI Biosecurity Assessments

Job not on LinkedIn

πŸ•’ October 22

Where this job comes from

Posted on SecureBio's careers page β†—SecureBio's careers page, not through a job board

First seen by Remote Rocketship October 22

Still open on SecureBio's site. Checked 1 hour ago.

Apply Now
Logo of SecureBio

SecureBio

11 - 50 employees

🧬 Biotechnology

πŸ”¬ Science

🀝 Non-profit

Biotechnology β€’ Science β€’ Non-profit

SecureBio is a nonprofit organization that works to secure the world against catastrophic pandemics by developing technology, policy, and operational solutions to delay, detect, and defend against biological threats. Its in-house researchers and partners in academia, industry, and government focus on pathogen-agnostic early warning (the Nucleic Acid Observatory using deep metagenomic sequencing), assessing and mitigating AI-driven biotechnology risks, and creating tools like SecureDNA for DNA synthesis screening. SecureBio also explores physical interventions (e. g. , PPE and far-UVC) and policy proposals to improve biosafety, biosecurity, and societal resilience to engineered or natural pandemics.

πŸ“‹ Description

β€’ Work with AI firms and internal research and engineering teams to conduct capability and safeguard assessments of emerging AI models β€’ Execute evaluation pipelines, analyze data, and identify how results align with threat models and risk levels β€’ Manually assess models for willingness and knowledge across specialized biology domains β€’ Synthesize findings into evaluation reports, technical write-ups, and risk summaries for partners and regulatory bodies β€’ Contribute to papers, reports, and the public dashboard of capability trends

🎯 Requirements

β€’ PhD in pathogen biology, microbiology, virology, or a closely related field; equivalent depth from other paths will be considered β€’ Wet-lab experience is preferred β€’ Strategic judgment about mapping evaluation results to real-world biological risk and technical safeguard performance β€’ Deep interest in safeguards, their failure modes, and contributory biological capabilities β€’ Ability to turn complex technical results into clear, well-structured writing β€’ Comfort with short, intensive project cycles and shifting priorities β€’ Roughly a year of coding in an industry or graduate research setting is preferred β€’ Working fluency in Python is preferred β€’ Direct experience with the Inspect AI framework, or building and evaluating LLM or agent systems, is preferred β€’ Familiarity with biosecurity policy, threat assessment, or counterterrorism work is preferred β€’ Experience working with AI developers or in a regulated or NDA-heavy environment is preferred

πŸ–οΈ Benefits

β€’ Comprehensive healthcare coverage, including health, dental & vision insurance β€’ Yearly mental health allowance for every employee β€’ Flexible work hours β€’ Unlimited paid time off (PTO) β€’ Minimum 12 weeks fully-paid parental leave β€’ Fully-paid conference sponsorships β€’ Yearly professional development allowance β€’ Employer 401(k) match up to 4% of total salary β€’ Referral bonus of up to $5,500 for successful candidate referrals

Apply Now

πŸ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

πŸ•’ October 22

Red Cell Partners

11 - 50

πŸ₯ Healthcare

πŸŽ–οΈ Defense

πŸ’Ό Consulting

AI researcher building evaluation frameworks, reinforcement-learning environments, and feedback systems. Helping Red Cell’s stealth startup advance reliable AI for healthcare, government, and regulated industries.

πŸ•’ October 18

ActiveFence

201 - 500

πŸ”’ Cybersecurity

πŸ€– Artificial Intelligence

Principal AI cybersecurity scientist researching frontier models, benchmarks, and security evaluations. Developing practical safeguards for Alice’s AI trust, safety, and security customers.

πŸ•’ October 18

ActiveFence

201 - 500

πŸ”’ Cybersecurity

πŸ€– Artificial Intelligence

Senior Responsible AI Researcher advancing frontier-model safety, evaluation, and adversarial robustness research. Building benchmarks and safeguards for Alice’s AI trust and security solutions.

πŸ•’ October 15

Dexcom

10,000+ employees

πŸ₯ Healthcare

πŸ’Ό Consulting

🏭 Manufacturing

Senior AI/ML Engineer researching foundation models and predictive AI for Dexcom’s continuous glucose monitoring products. Translating validated research into safe, regulated health technology.

πŸ•’ October 5

PostEra

11 - 50

πŸ₯ Healthcare

πŸ€– Artificial Intelligence

🧬 Biotechnology

Machine Learning Researcher developing agentic systems and adaptive models for PostEra’s AI-first biotech. Advancing computational methods that accelerate medicinal chemistry and drug discovery.

Built byΒ Lior Neu-ner. I'd love to hear your feedback β€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok