Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
Appen
AWS SageMaker
Data Annotation Tech
Labelbox
Mercor
Lionbridge
Document
Text
Image
Computer Programming/Coding
Text Generation
Fine-tuning
Evaluation/RatingAdvanced Computer Science specialist with extensive experience designing evaluation frameworks, benchmarking complex multi-turn LLM reasoning, and developing custom open-source tools. Proven track record of moving models past superficial optimization by engineering highly structured, atomic, and binary grading metrics. Expert in evaluating high-level programming domains including machine learning architecture, optimization algorithms, and low-level systems execution (Python, C++, ROS 2, Docker). Key AI Training & Evaluation Expertise: Evaluation Rubric Architecture (Outlier AI): Experienced in authoring, refining, and executing complex evaluation rubrics to align LLMs on code quality, security, and multi-turn logical consistency. Specialized in breaking down ambiguous prompt criteria into strict, atomic, binary data signals (eliminating subjectivity to ensure high inter-rater reliability) and configuring weighted negative-penalty parameters for structural or logic failures. Infrastructure & Automation (OpenClaw): Hands-on experience developing and interacting with OpenClaw, demonstrating deep familiarity with handling open-source backend structures, standardizing model outputs, and streamlining workflows for automated and human-in-the-loop data pipelines. Advanced Code Generation QA: Vetted to review, debug, and optimize complex coding outputs. Expert in evaluating edge cases for multi-threaded code, algorithmic complexity ($O(N)$ optimization), memory management, and specialized ML/robotics scripts. RLHF & Preference Tuning: Deep understanding of Reinforcement Learning from Human Feedback, prompt engineering, adversarial red-teaming, and generating hyper-specific "hard prompts" designed to stress-test model reasoning. Core Tech Stack for AI Training Languages: Python (Advanced/ML frameworks), C++ (Data structures & algorithms), SQL. Domains: Machine Learning (Inference, LLM security, neural search), Robotics & Systems (ROS 2, Docker, Kubernetes, Linux environment handling).
DocumentComputer Programming/CodingAuthoring, refining, and executing complex evaluation rubrics to align LLMs on code quality, security, and multi-turn logical consistency. Specialized in breaking down ambiguous prompt criteria into strict, atomic, binary data signals (eliminating subjectivity to ensure high inter-rater reliability) and configuring weighted negative-penalty parameters for structural or logic failures.
Masters, Computer Science
Bachelors, Computer Science
Graduate Machine Learning Researcher
Data Science Researcher
