vijaya kumari

Python, TypeScript, Machine Learning, LLM Evaluation,
Playwright, Claude API, Pinecone, Gradio,
Multi-Agent Systems, QA Automation

LLM Evaluation frameworks (TruLens, LangSmith),
MLOps (MLflow, FastAPI, Docker),
Quantum-inspired ML for LLM inference optimization

Discussions on LLM evaluation, AI reliability,
fintech AI systems, and #BuildInPublic projects.
Open to collaborations on AI safety and eval tooling.