I build AI, data, and automation systems that turn messy inputs into tools people can actually use.
If you need someone who can connect model behavior, data systems, APIs, and the automation around them, start with the broader portfolio or reach out on LinkedIn.
- Building retrieval, validation, and scoring systems across AI and data workflows.
- Shipping repo-native tools that bring geospatial, finance, and ML work into the same decision flow.
Private work: Purchase-Likelihood Scoring Pipeline · Geodatabase Validation Toolkit · ATS Scanner. More at works.estebanvalencia.com.
- Warp’s big bet on building open source with GPT-5.5 (OpenAI, 27 May 2026)
- 9 demos of Gemini Omni and Gemini 3.5 in action (Google AI, 29 May 2026)
- ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM (Hugging Face, 27 May 2026)
Benchmark pulse: I check LiveBench daily.
Live artifact. Go + GitHub Actions rewrites this every 6h and scores 6 AI feeds for recency and relevance. Source · LiveBench