AI / ML Engineer
I build AI/ML systems across model infrastructure, agentic RAG, and research-to-production workflows, with a background in physics and quantum computing.
Engineering
Production-style systems that show backend design, ML evaluation, agent workflows, and reproducible experimentation.
ML infrastructure platform for model registry, inference, evaluation tracking, async jobs, and benchmarking.
Agentic RAG backend for engineering knowledge, code, logs, tool calling, and grounded answers.
Research-to-production ML backtesting framework with leakage-safe validation and transaction-cost-aware evaluation.
Research
Research notes and projects connecting quantum computing, tensor networks, simulation, and machine learning.
Exploring compact tensor-network representations for supervised learning and interpretable model structure.
Research question
Can tensor network architectures provide useful inductive bias for small-scale image classification while remaining interpretable and computationally controlled?
Methods
Status: Active research notes
Notes and experiments around quantum feature maps, state preparation, and QML model behavior.
Research question
How do state preparation choices influence quantum machine learning experiments, and where do simple baselines reveal the real difficulty?
Methods
Status: Experiment planning and note consolidation
Research notes on imaginary-time evolution, simulation workflows, and numerical behavior.
Research question
How can double-bracket and QITE-style methods be organized into clear, testable simulation workflows?
Methods
Status: Notes in progress
Writing
Placeholder entries for technical notes and longer essays that will grow with the site.
A practical note on model versions, artifacts, metrics, and serving boundaries.
Workflow boundaries, retrieval quality, tool calls, and grounded answer design.
How temporal validation, costs, and baselines keep experiments honest.