Adam Moskowitz

About Adam Moskowitz

I\'m an AI and data systems engineer who builds production infrastructure from the ground up. At Skyward, I\'ve authored lines of Python powering AI pipelines, data warehouses, and automation systems that deliver measurable results — including a RAG system that generated FAQ pages and drove +24% clicks for a major client.I believe AI doesn\'t always need to be agentic to be powerful. Not every problem requires a multi-step autonomous agent — sometimes the highest-impact approach is embedding LLMs strategically within existing systems: a validation step here, an enrichment layer there, a generation pipeline with human-in-the-loop gates. The goal is structured, reliable, and scalable AI solutions, not AI for its own sake.My sweet spot is the intersection of systems architecture, data engineering, and applied AI. I design BigQuery data warehouses, build filtered RAG pipelines, develop multi-agent workflows when they\'re warranted, and create internal tools that make complex systems accessible to non-technical teams.Summa Cum Laude graduate from Stevens Institute of Technology (CS, 3.9 GPA), currently pursuing a Google Machine Learning Engineer Professional Certificate. Always looking for interesting problems to solve.Open to opportunities in AI/ML Engineering, Data Engineering, Solutions Architecture, and AI Consulting.

Experience

1. Automation and Technology Lead

   Skyward

   Apr 2025 — Present

   Promoted to Automation and Technology Lead in September 2025 after building the company\'s core AI and data infrastructure from the ground up. Currently lead the design and development of Skyward\'s AI and data systems, authoring lines of production Python powering the company\'s automation, AI pipelines, and data infrastructure.Key accomplishments:• Architected a BigQuery data warehouse from scratch — 100+ tables with full data governance, schema design, and 5+ automated ETL pipelines integrating GCS, GA4, Screaming Frog, Sitemaps, DataForSEO, and manual crawl data• Led the architecture of a large-scale AI-powered FAQ generation system with document embeddings using a custom RAG pipeline with multi-query retrieval and reranking, reducing input context by 97%• Scaled AI systems to generate FAQ pages for a single client; target pages saw +17% impressions and +24% clicks within 2 weeks of publishing• Developing multi-agent AI workflows for content generation and data processing with quality gates and automated publishing• Developed internal Streamlit tools for pipeline configuration, cost estimation, and data validation

Education

• Stevens Institute of Technology

  Bachelor's of Science, Computer Science