Olanrewaju Muili
Research Engineer & ML Researcher
Scientific Machine Learning · Trustworthy AI · Earth & Environmental Systems
U.S. Department of Energy Marine Energy Postgraduate Fellow
I build machine-learning systems for scientific and environmental problems, and study how autonomous systems can estimate when their own observations are trustworthy — making reliable decisions under uncertainty, corruption, instrument drift, and distribution shift.
Research at a glance
- DOE
U.S. Department of Energy Marine Energy Postgraduate Fellow
Research engineering with Deep Anchor Solutions — finite-element workflows and simulation-to-ML datasets.
- 2025
peer-reviewed ML publication
Sinkhole susceptibility via machine learning, Applied Computing and Geosciences.
- 0.882
Nash–Sutcliffe efficiency
HEC-HMS reconstruction of the Hurricane Florence rainfall–runoff response for a NC coastal-plain watershed.
- 625
prompt adversarial benchmark
Sole-authored LLM safety preprint: 98.9% recall at 0.0% false positives on the hard tier, across 18 attack categories.
- 5,000+
numerical simulations
Parametric finite-element runs generated for simulation-to-ML research at the DOE fellowship host.
- PyPI
public research software
tracevox-ai: open research environment for reproducible RL and trustworthy-AI experiments.
Methodology
Autonomous systems — agents, instruments, and automated experimental pipelines — usually assume their observations are reliable. In practice, channels go noisy, missing, corrupted, drifted, or contradictory, and nothing in the system notices. My methodological work asks whether a system can estimate the reliability of its own observations and adapt its decisions accordingly: trust-calibrated reinforcement learning, corruption-robustness evaluation, and reproducible experiment recording.
Formulation, experiments & limitations →View a recorded experiment
TraceVox
The engineering platform grew out of a broader interest in building inspectable, reproducible systems for evaluating AI behavior. TraceVox Research houses the research experiments; TraceVox AI focuses on production evaluation and observability.
TraceVox Research
An open research environment for reproducible experiments in trustworthy AI, reinforcement learning, multimodal agents, corruption robustness, adversarial robustness, evaluation, and AI safety — with recorded per-timestep traces, exact replays, and machine-readable published experiments.
TraceVox AI (Platform)
Engineering work around production AI observability, evaluation, tracing, safety monitoring, and agent/LLM infrastructure — the applied counterpart to the research environment.