Data-to-Model Interface Ownership: Own the data contract between the Data Engineer and the ML model stack. Define feature specifications, validate datasets against model input requirements, and escalate data quality issues before they reach the training pipeline.
ML Pipeline Contribution: Package models in Docker; contribute to CI/CD scripts under guidance; run inference tests and support deployment validation in product development environments.
- Local Services Search Team: Optimizes Local Service search experience, helping users discover catering, hotel, leisure and other life services. We apply LLM for query understanding, CTR/CVR prediction, local-service ai search card and agentic local service search framework.
Domain expert: You’ve scaled AI products in production and design for LLM failure modes such as hallucination, context degradation, prompt injection and latency under load.
Hands-on Technical Leadership: Stay technically involved and step in when needed to write code, debug issues, review architecture and resolve complex engineering problems.