Analytics Engineer with 2 years of production experience building data pipelines and automation systems, now transitioning to ML/LLM Engineering. I specialize in building scalable AI systems with a focus on LLM applications, agentic workflows, and MLOps practices.
Python • R • SQL • Bash • Linux
PyTorch • Scikit-learn • Transformer Architectures • BERT/Encoder Models • Fine-tuning (LoRA/PEFT) • Transfer Learning • Feature Engineering • Model Evaluation
LangChain • LlamaIndex • LLM APIs (OpenAI, Claude, Local) • RAG Systems • Prompt Engineering • Embeddings • Vector Databases (Pinecone, Chroma)
MLflow • Airflow • Docker • CI/CD (GitHub Actions) • Model Serving (FastAPI, Flask) • ONNX • LangSmith • Ollama • Model Monitoring • A/B Testing
ETL/ELT Pipelines • dbt • Python Automation • Apache Spark • Data Validation • AWS • Git/GitHub
Network Engineer - Automation @ MasTec QuadGen (2 years)
- Built end-to-end ETL pipelines processing network telemetry data for infrastructure optimization
- Applied time-series analysis and anomaly detection techniques
- Implemented Python and UiPath automation workflows, improving operational efficiency by 30%
- Collaborated with cross-functional teams to document and standardize data workflows
Master of Science in Data Science
University of Delaware | Expected May 2026
Focus Areas: Machine Learning • Deep Learning • Data Analysis • Applied Statistics • Multivariate Analysis
- LLM Applications: Building RAG systems and agentic AI workflows using LangChain and LlamaIndex
- Hybrid AI Systems: Exploring architectures that combine traditional ML/DL models with LLM reasoning for production deployment
- MLOps Practices: Implementing model deployment, monitoring, and CI/CD pipelines with Docker, MLflow, and ONNX
- Efficient Fine-tuning: Experimenting with LoRA/PEFT for resource-efficient model adaptation
