Sql, Pytorch, Python, uncertainty estimation, LLaMA-Factory, vLLM, RAG retrieval systems, context engineering, Harness design, reward model design, self-refine tool, MCP, regression comparison pipelines, training and inference frameworks, Verification, post-training of LLMs, FSDP, error attribution, evaluation-guided Agent optimization, Agent reliability analysis, Memory, search code interpreters, benchmark construction, verl, data pipelines, human annotation, LLM Agents, sandboxes