🌍 Based in Bay Area, California
📫 Reach me at [email protected]
💬 Let’s talk about: RAG pipelines, LLM integration, MLOps, and data systems at scale
I’m an AI Engineer with a strong foundation in data engineering.
My current focus is on Retrieval-Augmented Generation (RAG) and ML model integration, bridging enterprise internal resources with large language models to deliver smarter, context-aware AI systems.
I’m passionate about:
- 🧠 Designing RAG pipelines that connect vector databases and document stores
- ⚙️ Building and monitoring ML workflows using Airflow, MLflow, and Evidently
- 🧩 Integrating LLMs with enterprise knowledge bases and APIs
- 📊 Feature engineering, model training (XGBoost, LightGBM, PyTorch MLP)
- 🧱 Developing robust data and AI infrastructure with Docker and Kubernetes
Languages:
Python · Scala · Java · SQL · Rust
Frameworks & Libraries:
PyTorch · scikit-learn · LangChain · LanceDB · FAISS · XGBoost · LightGBM
MLOps & Data Stack:
Airflow · MLflow · Evidently · Docker · PostgreSQL · Spark · Hadoop · Hive
Cloud & Ops:
AWS · Azure · Grafana · Kafka · Jenkins · Linux
- Efficient vector indexing and retrieval for enterprise RAG
- LLM performance tuning (quantization, response latency)
- Connecting LLMs to real-world data sources with secure access controls
I swim like a fish and debug like a detective 🐠💻
- 🧭 GitHub: @fluffydog315
⭐ If you like my projects, consider starring them or collaborating on RAG and LLM integration ideas!