Senior AI Engineer focused on cost-aware LLM systems, AI agents, RAG, and production AI products.

I build AI systems across the full lifecycle: model development, evaluation, backend services, MLOps/LLMOps, Kubernetes deployment, monitoring, and business-impact optimization. My recent work includes ESA and EUMETSAT-related AI initiatives for satellite operations, multi-agent LLM workflows, synthetic QA generation for RAG evaluation, MLflow-based monitoring, and on-prem Kubernetes deployments with GitOps.

My current direction is building practical AI products and open-source tools that help teams move from promising prototypes to reliable, measurable, cost-aware production systems.

• Cost-aware LLM systems and inference optimization
• AI agents, RAG, and production LLM workflows
• Model evaluation, observability, and quality/cost tradeoffs
• MLOps/LLMOps for real deployment environments
• Open-source tools for AI product teams, startup CTOs, and senior engineers

• Improved synthetic QA generation quality from about 65% to about 80% by redesigning OCR integration, chunking, and LLM prompting workflows.
• Reduced token usage and latency by restructuring multi-step LLM generation pipelines and context management.
• Contributed to ESA and EUMETSAT AI initiatives across satellite health forecasting, telemetry anomaly detection, AI validation, and mission operations support.
• Reduced monthly cloud expenditure by about 35% / $32K+ in a previous data science role through cloud and model infrastructure optimization.
• Delivered ML and NLP systems linked to revenue growth, sales uplift, translation cost reduction, and campaign performance improvements.

Open-source toolkit for measuring and optimizing LLM, RAG, and agent workloads across cost, latency, quality, and reliability.

Current scope:

• prompt/model comparison reports
• token, latency, and cost tracking
• mock demos without API keys
• OpenAI-compatible provider support
• Markdown and JSON reporting

RAG and LLM application experiments, including a PDF chat application using LangChain, FAISS, and OpenAI embeddings.

Product-style macOS maintenance CLI with dry-run-first safety, local memory, rules, profiles, hooks, and scriptable output.

Applied data science, ML projects, and interview-style tasks from earlier stages of my career.

Python, FastAPI, LangChain, LlamaIndex, MLflow, Kubernetes, Docker, GitOps, Flux, Airflow, OpenTelemetry, AWS, GCP, PostgreSQL, MongoDB, Weaviate, PyTorch, TensorFlow, scikit-learn, Spark.

• Website: aidenerdogan.github.io
• LinkedIn: linkedin.com/in/aiden-erdogan
• GitHub: github.com/aidenerdogan