research-engineering

Research prototype for trace-based observability and failure analysis in retrieval-augmented generation.

Autonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.

C++/Python microstructure research engine for event-driven limit order book prediction and reproducible quantitative experiments.

A gated memory layer for trustworthy AI-assisted research workflows.

Real-time TUI for monitoring cloud GPU training instances

Automates hermetic environments (macOS/HPC) to eliminate drift. Provisions offline RAG (Gemma 2), compiles LaTeX manuscripts, and indexes local knowledge. Unifies infrastructure, writing, and inference into a single, audit-ready artifact.

Skill中间件架构：AI时代研究能力的工程化封装（以固定收益研究为例）

Research-to-production AI model release control plane connecting post-training experiments, baseline/candidate evaluation, regression analysis, safety/correctness checks, CI release gates, production telemetry, and evidence-linked SHIP · INVESTIGATE · HOLD decisions.

A Codex plugin that reduces over-design, hidden failure, and evidence inflation in research engineering.

Research-engineering portfolio: LLM evaluation, RAG, RLVR/post-training, machine learning, Rust systems, data engineering, and reproducible computation.

Factor-aware, physics-guided road-surface intelligence | 因子感知与物理引导的路面状态识别、摩擦可供性估计与可复现实验

Selected LLM, NLP, retrieval and vision-language research-engineering projects.

Reference model for managing state, intent, evidence, provenance, and execution in long-running agent-assisted research engineering.

Event-driven quantitative research evidence engine with real-data risk studies, leakage-safe execution, corrected inference, and reproducible reports.

Evidence-first A-share bottom-position and intraday-T research: leakage controls, risk filters, transaction costs, rolling OOS validation, and audit governance.

面向竞赛与实验论文的可审计、可复现工程化 Skill：实验评测、不可变基线、证据链与存量项目接管

Catch evaluation drift before it ships.

AI systems, quantitative research, and governed agent infrastructure.

Evidence-first research engineering lab for reliable AI agents, evaluations, and ML systems.

Route-aware evidence intelligence for LiFePO4 R&D.