Skip to content
View bonnie-mcconnell's full-sized avatar

Achievements

Achievement: YOLOAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: Pull Shark

Highlights

  • Pro

Block or report bonnie-mcconnell

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
bonnie-mcconnell/README.md

Hi, I'm Bonnie McConnell

CS + Statistics double major at Massey University, New Zealand. In my second year and building things to understand them.

I'm interested in the intersection between statistical thinking and software engineering: ML infrastructure, ranking systems, quantitative methods, and systems that can explain what they're doing and why.

What I'm working on:

  • adaptive-autocomplete - a ranking and suggestion engine built from scratch, with explainability built in from the start
  • model_monitor - production-style ML monitoring with drift detection, trust scoring, and safe model promotion

Background: Python is my main language. I use R for statistics work and have experience with C++, Typescript, SQL and Java. Comfortable with: NumPy, Pandas, FastAPI, PyTorch basics, Poetry, Git. Currently learning: systems design, distributed systems fundamentals, quantitative methods.

Degree: BSc Computer Science + Statistics, Massey University (2025–2027) GPA: 9.0/9.0

Open to internship opportunities in NZ, AU, or remote - summer 2026/27.

LinkedIn · bonniep.mcconnell@gmail.com

Pinned Loading

  1. model_monitor model_monitor Public

    Production-style ML model monitoring system with drift detection, delayed labels, retraining and safe promotion.

    Python

  2. adaptive-autocomplete adaptive-autocomplete Public

    Adaptive Autocomplete Core (AAC) is an explainable ranking engine built to demonstrate how real systems generate, rank, learn from, and explain suggestions.

    Python

  3. liminal liminal Public

    TypeScript library for LLM tool-use orchestration - DAG scheduling, SHA-256 content caching, typed errors, 323 tests.

    TypeScript

  4. backtesting-engine backtesting-engine Public

    Walk-forward backtesting engine with block-bootstrap Sharpe significance testing. Built from scratch in NumPy.

    Python

  5. kiwi-pulse kiwi-pulse Public

    Bayesian inference over noisy LLM sentiment signals - calibration testing, adversarial analysis, and uncertainty-gated decisions

    Python

  6. evalkit evalkit Public

    Rigorous LLM evaluation: bootstrap CIs, significance testing, automated auditing

    Python