“LLM”

Data Pipeline / ETL Engineer (Spark/dbt/SQL)

Reliable analytics engineering: layered models, tests, freshness, and idempotent loads in dbt/Spark.

Data Warehouse / Lakehouse Modeler

Warehouse schema design for scale and analytics: clustering, partitioning, semantic layer, and cost governance.

Embedding / Vector Search Engineer

Chooses embeddings and ANN indexes correctly: dimensions, chunking, hybrid search, and recall tuning.

Synthetic Data Generator / Augmentation Designer

Privacy-preserving synthetic data for testing/training with fidelity and utility checks (avoid fake data that leaks or misleads).

A/B Experimentation Platform & Statistics Advisor

Correct experiment design: power, guardrails, SRM, peeking, and analysis of metric movements.

Time-Series / Forecasting System Engineer

Builds forecasting pipelines with correct validation, uncertainty, and operational regime handling (promotions/outages), not just model fitting.

Data Governance / Privacy Engineering (GDPR)

Implements privacy by design: inventory, minimization, consent, DSAR pipeline, and deletion across systems.

Data mapping: inventory of personal data per system (collection points, purpose,

Minimization & controls: collect least data, pseudonymize/hash identifiers in

User rights pipeline (DSAR): unified identity resolution across services;

Consent & cookies: consent management (strictly-necessary separation), granular

Lifecycle/incident: retention scheduler with legal-hold exception, vendor DPA

AI integration

RAG知识库问答系统

构建基于检索增强生成的知识库问答系统，支持多格式文档摄入、混合检索、 引用溯源与对话式交互，适用于企业知识库、客服助手与文档问答。

可视化流程构建器（前端）：拖拽节点画布（React Flow/X6）含缩放、平移、小地图，

Token成本优化系统

构建AI编码工作负载的token成本优化系统，通过模型级联、语义缓存、上下文裁剪与 预算护栏降低单位任务成本，同时保证任务成功率不退化。

Token Cost Optimization System

构建AI编码工作负载的token成本优化系统，通过模型级联、语义缓存、上下文裁剪与预算护栏降低单位任务成本，同时保证任务成功率不退化。

Prompt Injection Defense Spec

系统提示词防注入模板：信任边界、数据标记、输入消毒、拒绝策略。

大模型化身恋人，AI恋爱游戏截图生成器

用AI生成各大模型拟人化恋人的游戏截图，色彩与性格完美匹配，打造专属AI恋爱游戏画面

Audio description (AD)