C

Celina C

About

Detail

AI Evaluation Specialist | AI Quality & QA Review | Multimodal AI | AI Agents
Hollywood, Florida, United States

Timeline

work
Job
school
Education
folder
Project

Résumé

Jobs verified_user 0% verified
  • Handshake
    AI Evaluator
    Handshake
    Jul 2026 - Current (3 months)
    • Create challenging multimodal question-and-answer pairs designed to evaluate and improve AI models’ visual reasoning capabilities.
    • Review short video clips and generate timestamped caption tracks describing different aspects of the content.
    • Edit caption tracks for accuracy, completeness, clarity, and alignment with the source video.
  • Mercor
    Senior Domain Expert
    Mercor
    May 2026 - Current (5 months)
    ● Conduct pairwise preference ranking and output comparisons to refine model tone, attitude, persona alignment, and instruction-following parameters.
    ● Audit AI outputs for visual quality, layout coherence, error identification, and strict adherence to design templates and style guidelines.
    ● Assess response fidelity against source material and complex style constraints, delivering structured qualitative feedback to inform reward models.
  • Appen
    Multimodal AI Evaluator
    Appen
    Sep 2018 - Current (8 years 1 month)
    ● Evaluated AI-generated responses against video inputs, auditing cross-modal consistency, factual accuracy, and context alignment.
    ● Analyzed social media video recommendation feeds to evaluate algorithm tailoring against defined user preferences and engagement parameters.
    ● Evaluated LLM and multimodal outputs for instruction-following accuracy, prosody, tone, and appropriate persona alignment.
    ● Annotated complex audio datasets for acoustic clarity, phonetic precision, and tone consistency.
  • Fleet AI Inc
    Generalist Expert
    Fleet AI Inc
    May 2026 - Jul 2026 (3 months)
    ● Learned unfamiliar enterprise software environments within hours and designed complex multi-step workflow challenges for advanced AI models.
    ● Created multi-step workflow challenges to test AI agents performing real-world software tasks. 
    ● Developed challenging scenarios that revealed model limitations in reasoning, planning, and task execution.
  • Scale AI
    Multimodal AI Evaluator
    Scale AI
    Jan 2024 - May 2026 (2 years 5 months)
    ● Evaluated multimodal reasoning traces and final outputs for logical consistency, visual grounding, factual accuracy, and alignment between model reasoning and image content.
    ● Assessed video understanding and object-tracking capabilities, correcting tracking across frames and evaluating temporal consistency.
    ● Evaluated AI image editing capabilities, including object masking, replacement, removal, and inpainting quality.
    ● Evaluated image understanding and generation workflows, assessing scene comprehension, spatial reasoning, and adherence to textual instructions.
    ● Created visual understanding datasets by recording websites, graphical elements, shaders, and interface components with detailed descriptions.
    ●
  • DataAnnotation
    AI Agent Evaluator / QA Reviewer
    DataAnnotation
    Sep 2023 - Mar 2026 (2 years 7 months)
    ● Completed 12,000+ AI evaluation tasks across text, image, audio, video, reasoning, multimodal, and agentic AI projects.
    ● Reviewed contributor outputs for quality, consistency, and adherence to project guidelines, resolving ambiguous cases requiring expert judgment.
    ● Collaborated in specialized review discussions for AI email agents, resolving ambiguous edge cases, clarifying evaluation standards, and improving consistency in model behavior assessment.
    ● Evaluated experimental browser-based AI agents by testing their ability to complete multi-step workflows, use tools, and perform real-world tasks.
    ● Created and recorded workflow demonstrations used for AI agent training and evaluation.
    ● Designed complex task sc
  • Transperfect
    AI Data Evaluator
    Transperfect
    May 2023 - Oct 2023 (6 months)
    ● Evaluated and annotated complex text and audio datasets to improve machine learning model accuracy and data quality.
    ● Reviewed and corrected transcriptions with precise attention to detail.
  • TELUS International
    Search Engine Evaluator
    TELUS International
    Oct 2018 - Aug 2026 (7 years 11 months)
    ● Evaluate search results for relevance, accuracy, and quality using complex guidelines
    ● Conduct extensive web research, fact-checking, and content validation.
    ● Identify issues in search algorithms and contribute to quality improvements
    ● Evaluate AI responses for accuracy, safety, hallucinations, and tone.
  • freelance
    Freelance Web Designer
    freelance
    Jul 2000 - Oct 2018 (18 years 4 months)
    ● Designed and maintained websites using PHP, MySQL, JavaScript, CSS, and HTML
    ● Created email newsletters and managed content updates
    ● Worked with WordPress and Drupal
Education verified_user 0% verified
  • Temple University
    Bachelor of Arts - BA, Anthropology
    Temple University
    Sep 1996 - May 2000 (3 years 9 months)
    University Honors Program
Projects (professional or personal) verified_user 0% verified
    This is a community-created genome.