I'm an AI/ML Engineer specializing in the next generation of intelligent systems. My passion is building and deploying robust, scalable applications powered by Large Language Models and Agentic AI.
When I'm not training models or debugging pipelines, you'll find me jamming to Red Hot Chili Peppers 🌶️ or hanging out with my corgi 🐕
- LLM & Agentic Systems: Engineering production-grade RAG pipelines, autonomous agents, and complex agentic workflows using LangChain, LlamaIndex, and PydanticAI—backed by vector stores like Qdrant, Pinecone, Weaviate, and pgvector.
- Model Serving at Scale: Deploying models to production via Kubernetes, KServe, gRPC, and serverless (AWS Lambda), with caching (Redis) and load balancing (NGINX) for low-latency inference.
- End-to-End MLOps: Building reproducible ML pipelines with MLflow, Weights & Biases, DVC, Airflow, Dagster, and Kubeflow—including model monitoring (Evidently, WhyLabs) and observability (Prometheus, Grafana, OpenTelemetry).
- Data & Streaming Infrastructure: Architecting real-time and batch data systems with Kafka, Spark, and DuckDB, plus cloud-native storage on AWS (S3, SageMaker, Bedrock) and GCP.
- Full-Stack AI Applications: Shipping end-to-end products with FastAPI backends, React/Next.js frontends, and PostgreSQL/Supabase for persistence.
⚙️ Core Languages
🧠 Machine Learning
🤖 LLM Development & RAG
🚀 Inference & Deployment
☁️ Cloud & MLOps
Cloud Platforms:
Experiment Tracking & Pipelines:
Monitoring & Observability:
🗃️ Databases & Storage
📈 Data & Streaming
🌐 Full-Stack
Have an interesting ML problem? Let's talk! Reach out via LinkedIn—I'm always open to discussing new projects, collaborations, or just chatting about the future of AI.