I’m Jeremiah, an AI Evaluation Specialist. I review LLM outputs, test multi-turn prompts, and build reliable datasets—with experience in analytics, lead generation, and AI-assisted front-end development.
I combine AI evaluation and model alignment work with data analytics and AI-assisted product development. My experience spans Outlier AI, Handshake AI’s Project Gaffer and Project Hedgehog, lead generation at Pearl Lemon Leads, and customer operations at Bulb Energy.
Across those roles, I focus on structured criteria, clean inputs, and clear documentation. A BSc in Business Administration and Management from POMA University gives me the business context behind the data.
AI Evaluation Specialist, Data Analyst, and AI-assisted Front-End Developer with experience in model alignment, complex data annotation, and product prototyping. Reviews LLM outputs for logic, multi-turn reasoning, accuracy, and usability, supported by a background in data quality, customer operations, and lead generation.
AI evaluation & model alignment
Structured AI response and code reviews at Outlier AI and Handshake AI for accuracy, logical coherence, safety, and instruction adherence.
Generative model response review across multiple evaluation cycles, including Handshake AI’s Project Gaffer and Project Hedgehog.
Root-cause analysis of hallucination patterns and documentation of standardized edge-case criteria.
Human-in-the-loop validation, output scoring, and dataset quality review.
Data cleaning and normalization, exploratory analysis, spreadsheet modeling, trend forecasting, KPI reporting, and dashboards. Microsoft Excel.
UI/UX & AI-assisted development
User journeys, wireframes, design systems, responsive layouts, rapid prototyping, usability review, and no-code/low-code concepts. Figma and Cursor.
Operations & communication
Technical and billing support, case management, documentation, CRM integrity, stakeholder reporting, prospect research, and lead acquisition. Zendesk, Salesforce, and HubSpot.
Professional experience
Outlier AI
Data Annotation Specialist
Dec 2025 – Present
Evaluate model responses and code outputs against accuracy, logical coherence, safety, and alignment guidelines.
Flag factual inconsistencies, bias, and edge-case failures.
Test multi-turn prompts and model reasoning boundaries.
Annotate complex datasets and domain-specific queries against quality requirements and output benchmarks.
Handshake AI
AI Evaluation & Data Specialist
Apr 2025 – Nov 2025
Reviewed generative model responses across iteration cycles, including Project Gaffer and Project Hedgehog.
Delivered structured feedback for prompt optimization.
Checked ingestion workflows for dataset cleanliness, label accuracy, and structural alignment.
Investigated hallucination patterns and documented systematic errors and standardized edge-case criteria.
Self-employed / freelance clients
AI-assisted Front-End & UI/UX Developer
Oct 2025 – Nov 2025
Prototyped, built, and deployed web interfaces and MVPs using AI-assisted development tools.
Designed user journeys, wireframes, and design systems.
Reviewed usability and refined layout, typography, and functional components.
Pearl Lemon Leads, United Kingdom
Lead Generation Specialist · Part-time
Aug 2024 – Sep 2025
Combined automated prospect research with manual verification to assemble structured lead databases.