AI Engineer / AI Automation Engineer

Core AI & Automation
- AI Engineering: Agentic AI workflows, tool/function calling, Retrieval-Augmented Generation (RAG), context compression, prompt engineering, evaluation, guardrails,

LLM observability.
- LangChain ecosystem: LangGraph, LangSmith.
- No-code/low-code automation: n8n (primary), Make, Zapier.
- Applied AI: Agentic AI adoption for demand forecasting, intelligent automation, cost optimization.

LLMs & Vector Search
- LLM providers: OpenAI (GPT-4 class), Anthropic Claude, others.
- Vector databases: Pinecone.
- RAG pipeline design: embeddings, chunking, hybrid search, reranking.

Machine Learning
- Regression modeling (linear, multiple, and regularized), feature engineering, model evaluation (R², RMSE, MAE).
- Data preprocessing, exploratory data analysis, and visualization for predictive modeling.

Frontend & UI
- Next.js, Tailwind CSS, shadcn UI.

Backend & Infrastructure
- Python (Flask, FastAPI, Pydantic, Pandas, NumPy, SQLAlchemy).
- Databases: PostgreSQL, MySQL, Redis.
- Cloud: AWS, DigitalOcean.
- Containers: Docker.
- Data lakes: AWS S3.

Observability & Monitoring
- LangSmith for LLM tracing, evaluation, and cost tracking.

Integration & APIs
- RESTful API design, webhooks, streaming responses.
- Real-time: WebSockets.
- Data formats: JSON, NDJSON, CSV, GeoJSON.

Notable Achievements
- Reduced automation costs through optimized workflows.
- Successfully implemented Agentic AI for intelligent demand forecasting.