Skip to content
Rodrigo Flores Bertolotti

Experience

  • Jun 2026
    – Sep 2026

    Mibanco — Credicorp

    Artificial Intelligence Intern · Lima, Peru 12°03′S

    Problem
    Recorded customer audio had to become structured, usable data for production workflows.
    Built
    A parallelized audio-ingestion and speech-to-text pipeline on Databricks with Azure AI Speech, plus a prototype LLM interpretation layer over the transcripts.
    Result
    Cut end-to-end runtime from 7 min per request — 20 min under load — to a stable 5 min; partially adopted on real customer calls at Peru’s largest microfinance bank.
    Stack
    Databricks · Python · SQL · Azure AI Speech

    the four-stage Databricks workflow, parallelized

    1. audio
    2. transcription
    3. encryption
    4. LLM feedback (prototype)
    5. email delivery
    • Built a parallelized audio-ingestion and speech-to-text pipeline on Databricks (Python, SQL) using Azure AI Speech, at Peru’s largest microfinance bank; now partially adopted on real customer calls
    • Cut end-to-end pipeline runtime from 7 minutes per request, degrading to 20 minutes under concurrent load, to a stable 5 minutes independent of load — by parallelizing the concurrent work and restructuring the code rather than adding compute
    • Prototyped LLM-based interpretation of transcribed speech, evaluating Azure AI models on output quality, cost, and workflow fit
    • Coordinated the AI team’s project planning while automating routine engineering tasks with LLM-assisted tooling

  • Nov 2025
    – present

    TRUE (Trustworthy and Responsible) AI Lab — Oregon State University

    Undergraduate Researcher, URSA Engage — LLM Reliability & Safety · Corvallis, OR 44°34′N

    Problem
    Hardware bit-flips can silently corrupt LLM inference — how robust are models, and what defends them?
    Built
    Robustness evaluations on the lab’s fault-injection harness, run at scale on an A40 Slurm cluster.
    Result
    Benchmarked 7 defenses against 2 attack classes across GSM8K, DROP and TriviaQA; co-authored a cross-scale resilience manuscript, now under review.
    Stack
    PyTorch · Hugging Face · Slurm
    • Evaluate robustness of Llama-3-8B to hardware bit-flip faults using the lab’s fault-injection harness (PyTorch, Hugging Face), run at scale on an A40 Slurm HPC cluster
    • Benchmarked 7 fault-tolerance defense configurations against 2 classes of adversarial bit-flip attacks (stealth and damage) across GSM8K, DROP and TriviaQA
    • Co-authored manuscript on cross-scale model resilience across 8B–32B target models, now under review; contributed experiments, benchmarks and the accuracy-versus-fault-tolerance trade-off analysis

  • Jan 2026
    – present

    Oregon State University Foundation

    Digital Technology Student Assistant · Corvallis, OR 44°34′N

    Problem
    Operational datasets needed to become institutional reports, and production web content needed upkeep.
    Built
    Data visualizations and summary reports from operational data; production web pages maintained in Sitefinity CMS.
    Result
    Reporting and web content delivered for institutional use.
    Stack
    Data visualization · Sitefinity CMS
    • Built data visualizations and summary reports from operational datasets for institutional reporting; maintained production web pages in Sitefinity CMS

  • Jul 2024
    – Aug 2024

    Universidad de San Martín de Porres

    Python Course Assistant · Lima, Peru 12°03′S

    Problem
    Students needed hands-on help with Python assignments and debugging.
    Built
    One-on-one mentoring, rubric-based grading, and recurring study sessions.
    Result
    Led 5+ study sessions and graded coursework against detailed rubrics.
    Stack
    Python
    • Mentored students on Python assignments and debugging, graded with detailed rubrics, and led 5+ study sessions