Protection Scientist, Engineer

🔥 3 minutes ago

🇬🇧 United Kingdom – Remote

⏰ Full Time

🟡 Mid-level

🟠 Senior

👷🏻‍♀️ Engineer

👻 Ghost score 25%

What it means: the chance that no one is really hiring for this job.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

10a Labs

WebsiteLinkedInAll Job Openings

11 - 50 employees

Founded 2021

🤖 Artificial Intelligence

🔒 Cybersecurity

☁️ SaaS

Artificial Intelligence • Cybersecurity • SaaS

10a Labs is an applied research and technology company specializing in AI security. It delivers intelligence collection, investigative research, and analysis for AI unicorns, Fortune 10 companies, and U. S. tech leaders. The company provides services that empower security teams and technology leaders to stay ahead of evolving threats, drive innovation, and protect their brands. Their work includes stress-testing AI models against threats, developing real-time threat detection systems, and monitoring cyber threats to enhance AI safety and security throughout the product development lifecycle.

📋 Description

• Identify and investigate misuse of the client's products, especially new types of abuse • Design and build systems to proactively identify and enforce against abuse on AI products • Establish robust abuse monitoring for new products and sustain monitoring for existing products • Prototype and incubate systems of defense against high-risk harms • Respond to and investigate critical escalations not caught by existing safety systems • Develop understanding of products and data • Scope and implement abuse monitoring requirements for new product launches • Improve monitoring operations and automate monitoring subtasks for existing products • Prototype and mature production systems for abuse detection, review, and enforcement • Collaborate with Product, Policy, Operations, Investigative, and Engineering teams to understand risks, develop responses, and build scaled tooling

🎯 Requirements

• Ability to work remotely on GMT and must be geographically located in the UK • Quantitative and coding background, including statistics/metrics • Proficiency in Python and SQL • Experience identifying, and ideally enforcing on, bad actors with scaled tooling • Ability to participate in an on-call rotation approximately once per quarter, resolving urgent escalations outside normal work hours • Ability to rapidly context switch across domains, modalities, and abuse areas, including violent activities and child safety • Background in machine learning and classification, especially on novel or poorly understood behaviours (desired, not required) • Experience scaling and automating processes, especially with language models (desired, not required) • Experience working with scaled labellers or reviewers (desired, not required) • Familiarity with AI safety, child safety, abuse by nation state and other malicious actors, digital mental health, fraud abuse, radicalization/persuasion/grooming, or hateful activities and groups (desired, not required)

🏖️ Benefits

• Full-Time (40 hours per week), contract position • Remote position based in London, UK • On-call rotation approximately once per quarter, including urgent escalations outside normal work hours, evenings, and weekends

📊 Check your resume score for this job

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

Upload Resume