Tim P.

Key Skills

Software

Mercor

Other

Toloka

SuperAnnotate

Scale AI

Remotasks

OneForma

Micro1

Lionbridge

Labelbox

Google Cloud Vertex AI

Appen

Top Subject Matter

RLHF Domain Expertise

AI Safety Evalution

Adversarial Testing

Top Data Types

Text

Image

Document

Top Task Types

RLHF

Text Generation

Bounding Box

Segmentation

Entity (NER) Classification

Classification

Object Detection

Question Answering

Text Summarization

Fine-tuning

Red Teaming

Transcription

Evaluation/Rating

Computer Programming/Coding

Data Collection

Prompt + Response Writing (SFT)

Freelancer Overview

AI Evaluation Specialist & Data Contractor (LLM Evaluation, Preference Ranking, Adversarial Testing). Brings 8+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Mercor and Other. Education includes Master's, Moscow State Linguistic University (2019) and Bachelor's, University of Toronto (2017). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and RLHF.

Labeling Experience

Independent AI Developer & Consultant (AI Automation for Structured Generation/Evaluation)

OtherTextRLHF

Built and shipped AI automation workflows that support evaluator-driven data generation for agentic and document-processing use cases. Integrated LLM tooling (Claude API and MCP) to enable structured memory retrieval and session continuity across multi-step AI agent workflows, supporting repeatable generation and output auditing. Led production pipeline development that includes prompt design and structured extraction outputs suitable for downstream supervised learning and evaluation. • Prompt/adjudication workflow support for structured generation • Agentic memory via MCP enabling consistent multi-step outputs • Structured extraction and document-to-report generation • Team training on AI-augmented workflows and prompt design

2022 - Present

AI Evaluation Specialist & Data Contractor (LLM Evaluation, Preference Ranking, Adversarial Testing)

MercorText

Performed high-volume LLM evaluations using structured scoring rubrics across multiple model families, assessing accuracy, instruction-following, coherence, and safety on thousands of outputs. Conducted prompt adjudication and comparative evaluation sessions to create preference-ranked datasets for downstream training. Executed structured adversarial testing and multi-turn behavior analysis to surface failure patterns and generate annotated classification data for alignment workflows. • Accuracy/instruction-following/safety rubric scoring• Preference-ranked dataset creation via prompt adjudication• Adversarial and multi-turn failure mode classification• Evaluator calibration and task-specific rubric alignment for SFT pipelines

2025 - 2026

Web Copywriter & SEO Specialist (AI-assisted drafting/QA)

OtherTextText Generation

Produced white-label SEO content at scale using AI-assisted drafting and QA processes to maintain editorial standards. Applied iterative review steps to ensure generated text met defined quality requirements and brand constraints. Although primarily content writing, the work included systematic auditing/QA of AI-assisted outputs for consistency. • AI-assisted drafting and quality review• Editorial standard compliance auditing• Scaled content production with QA gates• Iterative revision to meet client requirements

2020 - 2023

Education

Work History