Mercor
Mercor
51 – 200 Darbinieki
Mercor pieejamajā profilā nav pietiekami daudz pārbaudītas informācijas par uzņēmuma produktiem, pakalpojumiem, klientiem, darbības nozari vai personāla atlases fokusu, lai sagatavotu precīzu uzņēmuma aprakstu. Lai aprakstītu uzņēmumu vai tā piedāvātās iespējas, nepieciešams papildu avota materiāls.

AI Safety Red Teamer

Red-team frontier AI systems for Mercor partner labs by exposing vulnerabilities and assessing high-risk model behavior. Design adversarial prompts and help document safety findings.

Apraksts

  • Create adversarial prompts to test frontier AI models under pressure.
  • Find jailbreaks, unsafe outputs, hallucinations, and failures to follow policy.
  • Assess model resilience across misinformation, cybersecurity, biosecurity, fraud, political content, and other sensitive areas.
  • Record vulnerabilities and help prepare safety benchmarks and red-team reports.
  • Work with AI researchers to strengthen model alignment, resilience, and safety.
  • Complete projects for Mercor partner AI labs and enterprises training and improving AI systems.

Prasības

  • Bachelor’s degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related field.
  • At least five years of professional experience in AI safety, AI red teaming, trust and safety, cybersecurity, investigative journalism, life sciences, or a related field.
  • Strong analytical reasoning, prompt design, and written communication skills.
  • Experience creating adversarial prompts or evaluating frontier AI systems.
  • Experience with AI red teaming, RLHF, supervised fine-tuning, AI alignment, or trust and safety is preferred.
  • Familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methods is preferred.
  • Expertise in nuanced areas such as cybersecurity, biosecurity, political content, misinformation, or scientific safety is preferred.
  • Must be eligible to work in one of the listed locations.
  • Mercor cannot support H-1B or STEM OPT candidates at this time.

Priekšrocības

  • Work fully remotely.
  • Set a flexible schedule and complete work on your own timetable.
  • Receive weekly payments through Stripe or Wise.
  • Projects may be extended, shortened, or ended early based on project needs and performance.
  • Competitive pay.
  • Collaborate with leading AI researchers and safety teams.
  • Contribute to frontier AI safety and model development.
  • Earn up to $340 for each successful referral, subject to referral limits.
  • Reasonable accommodations are available upon request.

Saistītās vakances

NVIDIA

Senior Circuit Timing Engineer, NVIDIA (Remote, California)

NVIDIA

Design NVIDIA processor circuits for hardware security, adaptive clocking, and power management. Lead timing signoff and transistor-level analysis, and apply AI/ML methods to silicon design.

Atvērt
AT&T

AT&T Business Sales Representative, Territory Accounts — Memphis

AT&T

Build AT&T’s Memphis small-business and mid-market customer base by selling fiber broadband and other communications solutions. The role combines prospecting, account development, and consultative selling to grow territory revenue.

Atvērt