Felipe Santibañez-Leal

Felipe Santibañez-Leal

he/him

I&F Decision Science Assoc. Manager @ Accenture | Applied Scientific Researcher

Week in review: From developer portfolios to executive narratives

2 minute read

Published:

This week’s biggest change wasn’t technical – it was narrative. I restructured six industry portfolio entries to lead with business impact instead of algorithms. The shift reflects a real career evolution: from implementing models to owning their business outcomes.

The reframing

For years, my portfolio entries opened with architecture diagrams, framework choices, and model specifications. That made sense when I was the person writing the code. But the audience for a portfolio isn’t other developers – it’s decision-makers evaluating whether you can deliver results. So this week I rewrote the entries to open with KPI tables and strategic context before diving into technical details. Every project now starts with the question a VP would ask: “What did this do for the operation?”

Mining optimization pipeline

The numbers that matter

The difference is subtle but important. Saying “+100 TPH throughput gain via XGBoost ensemble” is a developer’s summary. Saying “+100 TPH throughput gain, translating to approximately USD 8-12M in additional annual revenue at current copper prices” is how the business sees it. Similarly, “15% reduction in environmental alerts” sounds like a model metric, but what it actually means is operational continuity – a mine that consistently violates environmental regulations can be shut down, and the regulatory exposure alone dwarfs the cost of the monitoring system.

Return on Investment

\[\text{ROI} = \frac{\text{TPH}_{gain} \times \text{hours}_{year} \times \text{copper\_price} \times \text{recovery}}{\text{project\_cost}}\]

The equation above is one I now include in executive summaries. It connects the model output directly to the financial outcome, which is ultimately what justifies the investment in data science infrastructure.

Developer to Technical Lead to Manager

Looking at the same projects through different lenses is a strange experience. When I built the throughput optimizer, I was proud of the feature engineering pipeline and the Kedro orchestration. When I led the team extending it, I was focused on code quality, testing coverage, and deployment reliability. Now, as the person accountable for the outcome, I think about whether the gain holds quarter over quarter, whether the operations team actually trusts the recommendations, and whether the ROI justifies expanding the approach to other plants. The same project, three completely different narratives – all of them true.

This reframing isn’t just cosmetic. It changes how you think about what to build next. When your mental model starts with the business outcome and works backward to the technical solution, you make different architectural decisions. You prioritize differently. You communicate differently.

Beyond the portfolio rewrite, this was also a productive week for the website itself: added 9 frontend screenshots, embedded 3 YouTube demo videos, and enriched 20+ rolling entries with SVGs and equations. The website is becoming a living technical portfolio – not just a list of projects, but a record of how my perspective on those projects has evolved over time.

You May Also Enjoy

Week in review: Vectorization, numerical stability, and biological accuracy

3 minute read

Published:

Modernizing eight research codebases at once sounds like a terrible idea, and some weeks it feels like one. But working across optics, biophysics, robotics, and geostatistics in parallel has surfaced a pattern: the same three engineering challenges keep showing up in every domain, wearing different clothes.

The first SOFI implementation in Chile, modernized

2 minute read

Published:

In 2012, I started working on Super-resolution Optical Fluctuation Imaging at SCIAN-Lab, Universidad de Chile, collaborating remotely with researchers at the III Physics Institute of the University of Gottingen in Germany. Working across continents and time zones with the Gottingen team was both challenging and exhilarating – SOFI was a relatively new technique at the time, and there was limited local expertise in Chile to draw on. Every implementation decision, from the cumulant computation pipeline to the deconvolution strategy, required careful coordination through emails and video calls, often debugging numerical issues with a six-hour time difference. The goal was to implement SOFI from the ground up – cumulant computation, synthetic quantum dot simulators, deconvolution – and apply it to biological samples. After months of work, we achieved the first successful SOFI super-resolution imaging in Chile, resolving structures below the diffraction limit using nothing more than temporal statistics from blinking fluorescent emitters. The pride of being the first group in Chile to produce these results was immense – it proved that cutting-edge computational optics could be done here, not just in European labs with larger budgets and established traditions in the field. That work contributed to a publication at SPIE Photonics West, presenting the cumulant-based framework and validation results.

Building a crusher wear management platform from scratch

2 minute read

Published:

Over the past few months I have been building an end-to-end software platform for managing crusher liner wear in minerals processing, working as a consultant for a mining equipment services company. It has been one of the most technically demanding projects I have taken on.