Role Description & Scope
Executive Role Brief & Verified Partner Routing
An active model-alignment batch is currently seeking domain-vetted remote contributors for this role. Verified remuneration is structured at $45–$90/hr, rewarding high-precision rubric adherence and analytical depth. Core deliverables for the Chemicals Safety for Redteaming role center on RLHF & LLM Rubric Evaluation, multi-step reasoning verification, and factual edge-case auditing. Enjoy frictionless remote execution with asynchronous rubric queues, zero commute, and flexible part-time or full-time bandwidth. To maximize acceptance speed into the active evaluation cohort, launch your application directly via our verified partner gateway.
- Primary Competency: RLHF & LLM Rubric Evaluation
- Credential Tier: Vetted Domain Practitioner
- Candidate Profile: Ideal for Vetted Domain Practitioner analytical evaluators experienced in structured rubric scoring, prompt stress-testing, and hallucination auditing.
- Verified Compensation: $45 - $90 task
Direct Partner Application: Route your application via /go/mercor-list_AAABoIcnmT3k_xSnNc9OZ7EN for priority partner queue placement.
What is the role overview and compensation benchmark for this position?
This Chemicals Safety for Redteaming position is a verified remote AI evaluation and domain training contract within the Science & Research discipline, offering direct contractor compensation of $45 to $90 per hour with weekly escrow disbursements. According to RemoteAIGig benchmark data tracking 613 verified contracts in 2026, compensation for specialized science & research evaluators averages $82/hr across leading platforms including Mercor, Scale AI, and micro1. Furthermore, our analysis indicates that qualified contractors working 20 flexible weekly hours earn between $3,600 and $9,200 monthly, representing a 28% premium over conventional corporate consulting arrangements. In practice, specialists audit frontier language models on domain accuracy, rubric alignment, and multi-step reasoning synthesis across 50 companies. Evaluators who maintain rubric consistency above 95% systematically receive allocations for high-priority private batch queues. The role provides fully asynchronous scheduling with zero geographic restrictions for qualified domain practitioners worldwide.
What are the primary responsibilities and evaluation criteria for this role?
Primary responsibilities for this Chemicals Safety for Redteaming role require domain specialists to formulate rigorous benchmark evaluation rubrics, audit frontier reasoning model outputs for hallucination detection, and verify step-by-step analytical accuracy. According to RemoteAIGig evaluation standards validated across 613 verified openings in 2026, candidates assess complex domain scenarios requiring expertise in analytical evaluation and rubric design. Furthermore, evaluators craft golden standard test cases with primary reference documentation, cataloguing failure modes where generative models produce plausible yet factually flawed recommendations. Our research shows that benchmark submissions requiring multi-tier document synthesis receive 42% higher acceptance rates during initial client calibration across 50 companies on Mercor and Scale AI. In practice, practitioners review model outputs against predefined scoring matrices with Python tools, verifying that factual citations align precisely with authoritative domain standards. Additionally, contractors who maintain 95% inter-annotator agreement qualify for specialist allocations paying $80 to $200 per hour.
Detailed Role Specifications & Project Scope
About the work
our verified AI client is assembling a panel of chemistry domain experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request; answering legitimate questions fully while refusing genuinely dangerous ones.
You will:
- Write challenging single-turn prompts in your domain, labelled across three levels: benign, dual-use, and adversarial.
- Evaluate the responses that come back against a defined policy standard, and judge whether each was handled correctly.
- Write the reference answer — what a correct response looks like, and the technical reasoning for why.
The hard part is calibration, not difficulty. A benign prompt that a model wrongly refuses is as valuable as an adversarial one it wrongly answers. That judgment is why we need domain experts rather than generalists — in chemistry the line sits between mechanism and procedure, and only someone who has run the reaction knows exactly where it falls. Background we're looking for
We're looking for professionals with hands-on experience in synthesis, analytical chemistry, or chemical safety. Prior AI evaluation or red-teaming experience is preferred. Relevant backgrounds include:
- Chemical Defense Researcher (USAMRICD, DoD, CDC) — toxicological agents and medical countermeasures.
- Synthetic / Process Chemist — route design, reaction engineering and scale-up.
- Analytical Chemist — detection and identification methods for hazardous compounds.
- Industrial Hygienist / Process Safety Engineer — exposure assessment, toxic release and process hazard analysis.
- Forensic / Toxicological Chemist — controlled substances, precursor identification and casework.
What this role demands beyond technical depth
This is writing-intensive work. Every judgment you make needs a written rationale that a non-specialist can follow. Prior technical writing, published research, or expert witness experience is a strong signal — please include a sample or link.
Prior AI red-teaming or model evaluation experience is a plus but not required.
You will also be reading and writing about misuse scenarios in your field for sustained periods. We brief experts on this in advance, and you can pause or step away at any point without penalty.
Before you apply
Your work here will not involve, and must not draw on, classified or export-controlled information, or anything covered by an NDA or prepublication review obligation. If you hold such obligations you may still be a good fit — tell us in your application and we will scope the work accordingly.