01 / Career trajectory

Experience

Each role gets its own line across the date map. Open a column when you want the work behind the title.

Company and role titles stay visible across the route.

Parallel practice
  1. University of VirginiaML Research Assistant
  2. Scale AIGenAI Technical Advisor Intern · SEAL
  3. Refraction Innovation HubSoftware Engineer Intern
  4. University of VirginiaB.S. in Computer Science
  1. ML Research AssistantUniversity of VirginiaTenureNov 2025 – May 2026LocationCharlottesville, VA

    Role description

    Inference-time activation-steering research focused on language-model visual bias.

    Selected impact

    • Built an inference-time activation steering pipeline for LLMs in PyTorch and NNSight, intervening on residual-stream activations across Qwen models with frozen weights.
    • Engineered a filtering pipeline over 616K+ COCO captions using lexical scoring, next-token probability disparities, and RMSE-based layer selection.
    • Reduced RMS next-token bias 28.9% while preserving output quality across 1,000 samples.

    Working set

    • PyTorch
    • NNSight
    • Activation Steering
    • Interpretability
  2. GenAI Technical Advisor Intern · SEALScale AITenureJun 2025 – Dec 2025LocationRemote

    Role description

    Frontier-model safety, evaluation, and agent reliability work on the Scale AI SEAL team.

    Selected impact

    • Red-teamed frontier LLMs in Scale AI SEAL, identifying jailbreaks, unsafe behaviors, prompt-injection risks, and agent security failure modes.
    • Produced RLHF-style code evaluation data for complex software-engineering and competitive-programming tasks.
    • Improved system prompts and tool use in agentic workflows to increase model safety, consistency, and multi-step reliability.

    Working set

    • LLMs
    • RLHF
    • Model Safety
    • Evaluation
  3. Software Engineer InternRefraction Innovation HubTenureJun 2025 – Aug 2025LocationMcLean, VA

    Role description

    Cross-platform nutrition and food-recognition product development across mobile, AI, and cloud systems.

    Selected impact

    • Architected a cross-platform food recognition app in TypeScript and React Native with OpenAI multimodal APIs.
    • Deployed authentication through AWS Cognito with storage on AWS RDS and Azure SQL across iOS and Android.
    • Improved load time 55% and reached 99.5% crash-free sessions through memory optimizations and lazy-loading monitored with AWS CloudWatch.

    Working set

    • TypeScript
    • React Native
    • OpenAI
    • AWS
  4. B.S. in Computer ScienceUniversity of VirginiaTenureMay 2026LocationCharlottesville, VA

    Academic details

    GPA 3.7

    Coursework

    • Computer Systems
    • Data Structures and Algorithms
    • Software Engineering
    • Cybersecurity
    • Machine Learning
    • Reinforcement Learning

    Focus areas

    • Computer Science
    • Cybersecurity
    • Machine Learning
    • Software Engineering