https://sergiomorapardo.github.io/work/Recent content in Selected work on Sergio A. Mora Pardo | AI/ML Technical LeadHugoen-UShttps://sergiomorapardo.github.io/work/personalized-product-discovery/Mon, 01 Jan 0001 00:00:00 +0000https://sergiomorapardo.github.io/work/personalized-product-discovery/<h2 id="the-problem">The problem</h2> <p>Affiliate product discovery depended on a static, curated landing experience. That limited the number of products users could explore and left little room for relevance to adapt to each session.</p> <p>The product opportunity was not simply to train a ranking model. It was to redesign the discovery system and prove, under controlled conditions, that personalization created incremental value across the funnel.</p> <h2 id="my-role">My role</h2> <p>I led the ML design for ranking and discovery, partnering across product and engineering to move from a curated landing to a continuous personalized feed. My contribution covered problem framing, ranking signals, experiment design, technical review, and interpretation of the results.</p>https://sergiomorapardo.github.io/work/causal-ml-remarketing/Mon, 01 Jan 0001 00:00:00 +0000https://sergiomorapardo.github.io/work/causal-ml-remarketing/<h2 id="the-problem">The problem</h2> <p>High-volume remarketing can optimize clicks while still sending messages to users who would have purchased anyway. The product needed to decide <strong>who</strong> should receive a message, <strong>when</strong> it should arrive, and <strong>what</strong> to recommend while measuring true incremental impact rather than correlation.</p> <h2 id="my-role">My role</h2> <p>I built and led the ML remarketing engine for push and email across eight Latin American countries. The work combined causal modeling, personalization, serving architecture, and a sustained program of controlled experimentation.</p>https://sergiomorapardo.github.io/work/production-ml-serving/Mon, 01 Jan 0001 00:00:00 +0000https://sergiomorapardo.github.io/work/production-ml-serving/<h2 id="the-problem">The problem</h2> <p>Personalized messaging required fresh behavioral context and low-latency decisions, but many useful ML features and scores were most reliable and economical to compute in batch. The serving design needed to connect both worlds without making campaign delivery depend on slow analytical queries.</p> <h2 id="my-role">My role</h2> <p>I designed the production serving architecture and its decision flow, aligning model computation, storage, APIs, session events, and product rules around the latency and reliability requirements of push and email delivery.</p>https://sergiomorapardo.github.io/work/applied-llm-evaluation/Mon, 01 Jan 0001 00:00:00 +0000https://sergiomorapardo.github.io/work/applied-llm-evaluation/<h2 id="the-problem">The problem</h2> <p>LLM prototypes can appear persuasive without being reliable. For personalized recommendations, the team needed an evaluation method that could separate candidate-retrieval quality from generation quality and make regressions visible before a live experiment.</p> <h2 id="my-role">My role</h2> <p>I led applied research on LLM systems for personalized recommendations and established the team’s initial offline evaluation methodology. I also guided the design of an MCP-based tool layer for supplying recommendation context to LLM-generated notifications.</p>