- Own production LLM pipelines end to end, from ingestion and multimodal model calls to structured records and storage.
- Design prompt and schema strategies to produce consistent, product-ready results.
- Build classification and filtering layers, including taxonomy mapping, audience filters, deduplication, and cleanup logic.
- Define and run evaluation harnesses, including golden sets, regression suites, and online metrics.
- Track and report against quality targets for completeness, duplicates, incorrect inclusions, image presence, and related product SLAs.
- Optimize token usage, model tiering, caching, and batching to manage cost and latency.
- Harden long-running asynchronous jobs with timeouts, partial recovery, memory limits, and safe production deployments.
- Partner with Flutter/mobile and QA teams on field contracts, review queues, and incident debugging.
- Document architecture and runbooks, and recommend model changes, fallbacks, or schema improvements.
PythonGCPPrompt Engineering