Welcome to Braedyn Thompson's portfolio!
See the roles I'm targeting →

Now playing
Berkeley Lab SeismicSoCal BearLM
ROLE I'M TARGETING

Machine Learning Engineer

Train models that beat a real baseline, then run them in production.

PyTorchLightGBMProduction MLPython · Java
SKILL CHECK . . . OK0.9998live detector ROC-AUC0.951magnitude R² in production48%below seasonal naive36engine unit tests

Skill map01

Each row points to the section below that shows it.

SkillWhereProof
Deep learningSeismicSoCala CNN → Transformer detector and a CNN → GNN → Transformer sizer
Training for live conditionsSeismicSoCallive-noise hard negatives; epicentre, pick and station-drop jitter
Forecasting at scaleBayRidershipone global LightGBM per quantile, 50 stations, 1 to 14 days ahead
CalibrationBayRidershipa split-conformal band whose label changes only when a back-test earns it
Time-series TransformersBerkeley LabPatchTST in NeuralForecast, lookback chosen by rolling CV
ML in a productAcademy of Testersa BKT + IRT engine as pure functions behind Spring Boot
Testing ML codeAcademy of Testers, SeismicSoCal36 JUnit tests; pytest and a daemon selftest in CI
Serving and promotionSeismicSoCalevery 2 s per station on a free ARM VM; a six-rule promotion gate

SeismicSoCal · two models serving a live stream02

A live earthquake detection system on 19 seismometers across Southern California. Two PyTorch models run on a free ARM VM, scoring every station every 2 s.

0.9998Detection ROC-AUC7,303 held-out windows
0.951Magnitude R²937 held-out quakes
0.25%False triggers on live noiseat the live 0.6 threshold

  • 01

    Built the detector as a CNN → Transformer over a 30 s window, with the P-wave anywhere in it and 2,062 hard negatives: real live-stream noise that once fooled a detector.

  • 02

    Built the sizer to separate shape from size: each window is normalised to unit peak so the CNN reads shape, while log peak velocity and distance are graph-node features. Two graph-convolution layers (Gaussian distance weights, σ = 50 km) and a Transformer across stations feed the head.

  • 03

    Trained under live conditions: the epicentre jittered by ~8 km, picks by ±0.5 s, and stations dropped at random.

  • 04

    Kept 5 seeds rather than 10 after a seed study showed ensembling added only +0.003. The same pipeline.py runs live and in replay, and checkpoints carry their normalisers and station list.

  • 05

    Put promotion behind QuakeOps: a retrained model goes live only through MLflow tracking and a six-rule statistical + replay gate.

BayRidership · global quantile forecasts, retrained weekly03

A Bay Area transit analytics platform I built end to end. Its forecast covers every BART station two weeks out, with a band that says how often it holds.

48%Lower MAE than seasonal naive283 vs 549
14Days aheadall 50 stations
73%Band coverageagainst an 80% target

  • 01

    Framed each training row as a station, a forecast origin and a horizon, with features that use only data up to the origin. Values are scaled by each station's 28-day level, so one model fits Embarcadero and the quietest suburban stop alike.

  • 02

    Trained one global LightGBM model per quantile (p10, p50, p90) instead of one model per station.

  • 03

    Back-tested walk-forward over 12 origins: the first 6 for calibration, the last 6 for testing. The improvement's 95% bootstrap interval is 200 to 340 entries a day.

  • 04

    Calibrated the band with rolling split-conformal prediction. It held 73% against an 80% target (the Christmas fold alone is 44%), so the site calls it a “calibrated model range”, not an 80% range.

  • 05

    Retrained every Monday with a run log of every metric and CI; FastAPI on Cloud Run serves the forecasts.

Berkeley Lab · PatchTST in practice04

Data Science & ML Research Intern at Lawrence Berkeley National Laboratory (ESnet), Sep 2026 – present, forecasting traffic at the regional data caches that serve CMS physicists.

24%Lower RMSE than persistenceevery variable and horizon
15Tokens from a 128-day window16-day patches, 8-day stride

  • 01

    Ran NeuralForecast's PatchTST on PyTorch Lightning with RevIN on and early stopping on validation loss.

  • 02

    Made the patch follow the lookback: 16-day patches with an 8-day stride once the window is long enough, and half the window for very short ones, since a patch can't be longer than its input.

  • 03

    Standardised each variable, because counts and data volumes live on very different scales.

  • 04

    Chose the lookback by rolling-origin CV, and tested the loss and percentile forecasts as experiments instead of leaving defaults.

Academy of Testers · an adaptive engine in production05

A full-stack AP/SAT study platform I built as ML & AI Software Developer (Jan 2023 – Jun 2026). The adaptive SAT engine and the RAG essay grader both run in the live product.

8Skills per studentone mastery vector
36JUnit testsno Spring, no database
-23%Grading errorRAG grader vs. naive LLM

  • 01

    Wrote the engine as pure functions with no Spring, no repositories and no now(): clocks and data are passed in, so all of it is testable without a database.

  • 02

    Damped BKT updates (25% of a gain, 50% of a loss) with a guard so a miss never raises mastery; a miss also bleeds into prerequisite skills at κ = 0.35.

  • 03

    Applied forgetting lazily on read in MasteryService, the only place weights are read, so a stale value can't leak out.

  • 04

    Scored candidate questions as 0.45 × skill gap + 0.40 × Fisher information − 0.15 × recency, then sampled from the top 5 with a softmax (τ = 0.15). The client does no model math.

  • 05

    Ran the essay grader on GPT-4o at temperature 0 with constrained JSON output, grounded in retrieved rubric clauses and scored exemplars.