Jordan Browne-Moore

Machine learning engineer, London, UK

I build machine learning systems for regulated finance, and I study how language models work on the inside.

Resume Email

Illustration, not data: bootstrap learning curves settling to a floor. The fit, instability ≈ k/n^α + floor, is the feature-stability method behind the 50% default reduction; my refusal-steering write-up proposes the same machinery for its next step.

Applied work

Independent research

  • The refusal axis rotates ~90° between consecutive transformer blocks, so single-vector steering hits a geometric ceiling.

    The refusal axis is layer-local

    Measured across Qwen3.5-9B and Mistral-7B on BeaverTails, 12 harm categories. Pushing toward refusal is cheap; pushing toward compliance degrades output before producing it.

    Extends the refusal-steering method of García-Ferrero, Montero & Orus (arXiv:2512.16602). My own results, cross-checked against the committed data: 12 of 12 claims reproduce.

    activation-steering-asymmetry on GitHub

  • Zero autonomous self bootstrap in 1,332 mundane control trials; tool response poisoning produces about 36% pooled compliance.

    Self bootstrap exfiltration in open weights agents

    20+ configurations across 9 families (12 to 120B), ~14,000 real trials, escapement harness, open source.

    escapement on GitHub

  • LLM activation steering toolkit

    Python research toolkit for fine-grained control of LLM refusal behaviour. Domain-aware activation steering with per-category vectors, going beyond simple abliteration to independently target specific behaviour types.

  • Feature bootstrapping toolkit

    Bootstrap learning curve framework for feature stability testing in production ML models. Determines how much data a feature needs before its predictive signal stabilises.

Writing

Background

Experience

  • Senior Data Scientist, then Consultant, Kuda Technologies

    Hired to build the credit risk and fraud detection functions from the ground up. Retained as external consultant to continue leading these workstreams after transitioning out of the full-time role. Owned model development, validation methodology, and production deployment across credit scoring, KYC automation, and fraud detection. Mentored 4 data scientists and participated in cross-seniority hiring.

  • Data Scientist III, CB Insights

    LLM fine tuning, NLP, production ML engineering.

  • Senior Data Science Consultant, Capgemini

    Financial services consulting.

  • Data Science Consultant, Beyond Analysis

Education

  • MSc Financial Economics, Birkbeck, University of London

  • BSc Economics & Finance, Southern Oregon University

Contact

Resume Resume PDF

Book a short intro call