Dec 2025 → Present
Apron — Vietnamese Locale LLM Eval Harness
LangGraphFastAPINext.jsTanStack QueryZustandLiteLLMLangSmithAWS Bedrock
- Built LangGraph evaluation workflows for Vietnamese coding-locale benchmarks with stateful routing, pass/fail gates, and regression batches for instruction-following and tool-use scenarios.
- Routed LLM judge and verifier calls through LiteLLM with Azure OpenAI and AWS Bedrock fallback for rubric scoring and structured output validation.