I build models that predict the physical world, and study where they stop being right.

Autonomous systems and multimodal detection in practice; world models and representation learning in research.

Junior ML Engineer at Hertz New Technologies.

Experience and education

0.01%
True pathPredictionsSpreadPredictions of the Hénon map, each starting within the uncertainty of the true state. Chaos widens the fan until the prediction says nothing: here after 15 steps. Anchor works on the harder case, where the uncertainty comes from noisy, partial observations.

Selected work

Anchor

Multi-step consistency targets for latent world models

An auxiliary loss that pulls a world model's multi-step rollout toward targets anchored in real observations. The theory says when it is harmless and when it must help; the experiments so far confirm the theory and have not yet shown an advantage over the standard target.

Status
In progress
Topics
world models, self-supervised learning

Drone Audio Detection

Acoustic early warning, and where it breaks

A Random Forest classifier on MFCC features with local inference, reaching strong held-out metrics that then failed on real recordings while misflagging ambient noise. The generalization gap, not the accuracy number, is the finding.

Status
2026
Topics
audio ML, sim-to-real, embedded

All projects

Achievements

Detect & Defend — European Defence Tech Hackathon

Built DetMesh, a multimodal counter-UAS system combining audio, RF, and vision for drone detection. The work later became Umbris.

Result
1st place
Year
2026

Spaceshield Hack

AgloMeter, a data-driven analysis of transport exclusion and accessibility. Led the team as project manager.

Result
1st place, Space category
Year
2026

All achievements