LLM Evaluation API
A flexible API for evaluating LLM deployments, fine-tunings, prompts, and models with configured metrics across cloud and self-hosted endpoints.
PythonCloud RunQdrant
Selected work from recent cloud data, AI/ML, analytics, and platform engineering projects.
A flexible API for evaluating LLM deployments, fine-tunings, prompts, and models with configured metrics across cloud and self-hosted endpoints.
An event-driven GCP platform where SMEs define heuristic processes on incoming data and trigger alerting workflows.
A controlled cloud analytics environment for customer data analysts and scientists working with centrally stored data.
An ETL and ML model serving workflow for inferential materials planning, including model tracking, KPIs, and scaling.