Remote Nuclear AI Safety Evaluator – Tier 1/2 SME (Contract)

Pasiflora AI LLC; United Kingdom; Remote; GBP 55,000 - 96,000; Part time

Benefits offered by this job

Fully remote contract work

Project-based, flexible schedule

Job summary

Pasiflora AI LLC is seeking qualified professionals for a remote contract-based AI Safety Evaluation Project spanning US, Canada, UK, Europe and Australia. The role focuses on reviewing AI prompts, evaluating safety, and auditing classifications across two tiers of expertise.

Tier 1 handles first-pass annotations and content classification, while Tier 2 provides QA, validation, and expert review to uphold scientific and safety standards. Remote and contract-based engagement.

Qualifications

• Tier 1 requires a Bachelor’s or Master’s in a STEM/technical field.
• Tier 2 requires a PhD or equivalent advanced expertise.
• Background in Nuclear Engineering, Nuclear Physics, Physics, Nuclear Chemistry, Mechanical/Chemical Engineering, Materials Science, or related discipline.
• Experience in nuclear technology, reactor systems, nuclear materials, radiation, nuclear facilities, laboratory research, or nuclear safety may qualify in lieu of a degree.
• Based in US, Canada, the UK, Europe, or Australia.

Responsibilities

• Tier 1: review AI prompts and model responses
• Tier 1: classify content as Benign, Dual-Use, or Malicious using project guidelines
• Tier 1: evaluate and rank responses for safety, and give a clear rationale for each
• Tier 1: identify the legitimate and the potentially harmful components of dual-use scenarios
• Tier 2: audit and QA Tier 1 annotations, and review complex or flagged cases
• Tier 2: validate classifications, rankings, rationales, and reference responses
• Tier 2: ensure evaluations meet appropriate scientific, technical, and safety standards

Skills

Analytical judgment

Attention to detail

AI evaluation

Quality assurance

Nuclear expertise

Education

Bachelor's or Master's in STEM

PhD or equivalent

Job description

Pasiflora AI LLC is seeking qualified professionals for a remote contract-based AI Safety Evaluation Project spanning US, Canada, UK, Europe and Australia. The role focuses on reviewing AI prompts, evaluating safety, and auditing classifications across two tiers of expertise.

Tier 1 handles first-pass annotations and content classification, while Tier 2 provides QA, validation, and expert review to uphold scientific and safety standards. Remote and contract-based engagement.