HomeAboutProcessSourcingSystems & AIAI Work RadarCommercialBlogResearchContactBook a 15-Min Clarity Call
Verified Active RoleAI TRAINING AND RLHFRemote

Senior RLHF & AI Evaluation Specialist

ScaleLogic AI LabsRemote (Worldwide)Ref ID: OPP-AWR-2026-001

About the Opportunity

Lead expert evaluation benchmarks for reasoning LLMs, develop safety grading rubrics, and calibrate reward model signals.

Key Responsibilities

["Design and execute rigorous human-in-the-loop evaluation rubrics for frontier reasoning models.","Perform adversarial red-teaming across technical, logical, and safety vectors.","Analyze model failure modes and construct calibrated preference datasets for direct preference optimization (DPO)."]

Requirements & Eligibility

["3+ years in AI evaluation, NLP benchmarking, or technical prompt engineering","Strong analytical writing and precision testing mindset"]

Key Skills & Competencies

RLHFPrompt EngineeringPythonLLM EvaluationDPO/PPORubric Design

Role Overview

Hiring Entity
ScaleLogic AI Labs
Work Mode
Remote
Location
Remote (Worldwide)
Employment Type
Contract
Experience Level
Mid-Senior
Last Verified
Sep 13, 2026
PulseLifeX Referral & Verification Guarantee

Verified Active Role: This listing has been verified directly against the official employer careers portal.

Direct Official Routing: When you submit Quick Apply, your referral trail is recorded and you are immediately redirected directly to the official employer ATS.

PulseLifeX is an independent talent intelligence platform and never charges candidate fees.