Experience

Designed and evaluated world-model architectures for spatial reasoning, improving long-horizon prediction accuracy by ~18–25% on simulated navigation and embodied AI benchmarks.

Led experiments across 10k–100k+ simulated trajectories, developing data pipelines and evaluation metrics that reduced training instability and cut experiment iteration time by ~30%.

Implemented relational spatial reasoning modules inspired by quantum entanglement to model object-to-object and scene-level constraints, reducing combinatorial search overhead; collaborated within a 5–8 person research team on reusable research code and publications.

Worked on ML-driven big data analysis and predictive modeling for Artemis I’s Orion spacecraft trajectory and propulsion systems, integrating algorithmic insights with real-world hardware and flight control simulations.

Collaborated with SRAG (Space Radiation Analysis Group, JSC) to correlate onboard FDIR fault events with real-time space weather and SAA transit data, supporting predictive modeling of radiation-induced SEUs in flight avionics and informing ops constraints during high-intensity crossing windows.

Architected Project Callisto (internet-independent voice AI on a human-rated spacecraft): retrained Alexa wake-word CNN for 60–70 dB cabin acoustics, driving near-zero false-positive activations through hardware validation at Lockheed Martin (Denver).

Owned OpNav end-to-end for Artemis I; processed 1,000+ images across 26 passes, achieved 3σ certification in 4 passes, qualifying autonomous return navigation if DSN contact were lost at 384,000 km. · Flight-certified

GN&C software to NASA NPR 7150.2 Class A within cFS; implemented UDU covariance factorisation across 500+ Monte Carlo trajectories, cleared the pre-launch OIMU-1 anomaly at Flight Readiness Review, and delivered 0 open MISRA C:2012 Required-rule findings.

Built a DSN latency-tolerant transport layer and Artemis I BET reconstruction; replaced TCP at 2.56 s RTT with CCSDS-native FEC enabling live Mission Control video from 384,000 km, and fused 5 data sources post mission into ground truth for Artemis II algorithm updates.

Mentoring and leading AI/ML workshops for undergraduates

Organizing hands-on sessions on deep learning and classical mathematics