Applied models measured from training to inference
AI/ML Engineer
My applied ML work is developing across anomaly detection and multimodal inspection. I am connecting dataset preparation and model evaluation to deployment constraints: combining vision with operational metadata, comparing practical baselines, optimizing inference, and preserving records that allow predictions to be reviewed.
Why this direction fits
I combine model-focused work with systems thinking, so evaluation targets, inference performance, API contracts, and auditability are considered alongside training quality.
Current evidence
BCA in Information Technology, Oracle Data Science Professional, IBM AI Literacy, CheTech Hackathon first place, and two applied-ML systems in progress.
01 / CAPABILITY MAP
How I would contribute
Modeling
XGBoost, anomaly baselines, PyTorch workflows, YOLOv8, and multimodal feature direction.
Computer vision
OpenCV preparation, object detection, category confidence, and reviewable bounding-box outputs.
Inference
ONNX Runtime optimization, CPU-oriented serving, FastAPI contracts, and target benchmarks.
Evaluation
Dataset-aware metrics, error analysis, target mAP and FPS, and traceable anomaly records.
02 / VERIFIED SKILLS
Role-aligned toolkit
- Python 3.13
- PyTorch
- XGBoost
- YOLOv8
- OpenCV
- ONNX Runtime
- Pandas
- FastAPI
- PostgreSQL
- MLflow
03 / SELECTED WORK
Evidence for this role
Multimodal Defect & Threat Inspection System
A multimodal inspection pipeline combining lightweight vision models, signal metadata, optimized inference, and anomaly records.
- Target: 42 FPS edge inference
- Target: 94.2% mAP across five categories
Production MLOps Anomaly Detection & Deployment System
A versioned anomaly pipeline with experiment tracking, drift monitoring, autoscaling, rollback triggers, and observable serving.
- Target: automated drift visibility
- Target: safe rolling updates with rollback
Enterprise Multi-Agent Knowledge & Research Assistant
A cyclical Planner, Retriever, and Fact-Checker workflow combining hybrid and vectorless RAG with enterprise guardrails.
- Target: 34% lower context hallucination
- Evaluate: faithfulness · relevancy · recall
04 / TAILORED RESUME
Resume for this role
AI/ML Engineer
This version will foreground the experience and project evidence most relevant to this hiring path.
- —Applied modeling and computer vision pipelines
- —Evaluation, error analysis, and target benchmarks
- —Optimized inference and auditable serving