Luis P. Perez
AI/MLDataCompliance & RiskFintech
I turn complex, high-stakes domains into trusted products and systems—from real-time risk decisioning and compliance platforms to ML detection and foundational data products. I’m now applying that experience to GenAI and agentic systems.
The throughline
AI is an evolution of the work—not a reinvention. Each chapter has added a layer of technical depth to the same core challenge: turning complex signals into useful, explainable action.
Selected impact
Selected outcomes across risk decisioning, compliance automation, and ML.
Led the product organization that moved more identity and risk decisions into the real-time transaction flow, enabling eligible customers to send higher values while applying friction where risk justified it.
Xoom / PayPalDuring a major PEP database migration, identified a persistent entity identifier, formed a matching hypothesis, and validated it with a controlled batch—preventing a major analyst-review backlog.
Block / SquareSet the strategy, evaluated multiple models, independently analyzed score stability to address customer-experience concerns, and helped productionize a conversion-propensity model.
DisneyExperience
Roles spanning integrations, product leadership, compliance technology, ML, and foundational data.
Identity data products; previously Paid Sharing detection. Lead product strategy for foundational identity data assets used by DS, MLE, and Analytics.
Compliance technology. Joined as the org’s first TPM, translating Compliance, Legal, and Engineering requirements into delivery across customer screening, transaction monitoring, and case management.
AML platform and financial data. Led product for an AML startup, shaping a standardized data model and guided investigation experience for compliance teams.
Risk, KYC, payments, and people leadership. Built and managed a four-PM Risk Product organization spanning real-time KYC, internal tools, and platform modernization.
International payments integrations. Translated partner API requirements into repeatable technical specs, bridging discovery and implementation before Xoom’s acquisition.
AI, data & technical leadership
I work at the boundary between product, domain expertise, data, and engineering—hands-on enough to investigate, prototype, and reason about implementation choices.
My GenAI work builds on years spent shaping systems that retrieve signals, apply policy and models, manage uncertainty, support human judgment, and produce auditable outcomes.
Over a decade of decision-systems experience underpins that shift, backed by a Databricks context engineering certification and hands-on prototyping in agentic systems.
Technical builder
My independent automated trading and backtesting platform is where product judgment meets hands-on systems work: modular broker integrations, automated execution, performance analysis, parameter experiments, and ML prototypes.
Leadership
Grew and managed a four-person PM team, developed one into a people manager, and aligned Product, Engineering, Compliance, Legal, Operations, Data Science, MLE, and Analytics around decisions where customer outcomes and risk collide.
Posts
Writing about technical product craft, experimentation, automated trading systems, and what I learn while building.
My 0DTE bot opened a position late enough that its configured time stop landed after the market close.
Read post →My 0DTE bot submitted an entry, spent about a minute failing to confirm the fill, logged Aborting, and went back to scanning for signals.
Read post →An autonomous trading bot is convenient until I decide, mid-session and away from my computer, that it should stop.
Read post →When a strategy has been backtested hundreds of times, “which run was that?” stops being an administrative question. It becomes part of the ev...
Read post →My candle-based backtest liked a 0DTE options strategy. The live system did not.
Read post →