Applied AI & ML
Statistical reasoning, computer vision and multimodal learning. Connecting data strategy and model development to a concrete engineering need.
Applied AI Lead · AI Systems · Automation · Multimodal AI
Evelyn Gutierrez, PhD
Complex problems.
Practical AI systems.
I turn complex and ambiguous problems into practical AI solutions.
With more than a decade across data, machine learning and applied AI, I work from problem framing and experimentation through system design, prototyping, validation and production-oriented engineering.
A CONNECTED TRAJECTORY
Statistics → Machine learning → Computer vision → Industrial AI → GenAI → AI systems
01 / Expertise
Depth in AI.
A view of the whole system.
Choosing the right approach means understanding the problem, the evidence and the environment where a solution needs to work.
GenAI, RAG & Agents
Technical knowledge assistants, retrieval systems and agent workflows. Building prototypes and evaluating their answers against domain expectations.
AI Systems & Integration
AI systems design with attention to APIs, data flows, evaluation and production constraints. Collaborating across software, cloud and architecture teams.
Technical Direction
Turning ambiguous needs into feasible approaches. Comparing options, defining prototypes and using expert feedback to guide technical decisions.
02 / How I work
From the real need
to a usable system.
I contribute across the AI lifecycle, with evidence and domain feedback shaping each next step.
- 01
Understand
Clarify the users, constraints, available data and success criteria.
- 02
Structure
Turn ambiguity into a tractable problem and identify the highest-value use cases.
- 03
Design
Compare approaches and define components, interfaces and evaluation strategy.
- 04
Build
Develop pipelines, models, agents, APIs and demonstrators hands-on.
- 05
Validate
Measure performance and collect expert feedback against realistic needs.
- 06
Industrialize
Work with engineering teams on reproducibility, integration and operational constraints.
An iterative process: what we learn in validation informs what we build next.
03 / Selected work
Applied problems.
Evidence that matters.
Selected contributions across industrial AI, knowledge systems and research. Industrial projects are anonymized.
Applied AI Lead
AI Solutions & Automation
From opportunity framing and solution design to evaluation, integration and production-oriented delivery.
01 / Industrial computer visionAI solution · Production validation
Making visual inspection
work on the production line.
Industrial computer-vision quality inspection carried from requirements and data strategy through model development, deployment and production follow-up.
>95%on relevant evaluation metrics
~1/minvehicle cadence in the production context
Several classes reached around 99%. Results are class- and metric-dependent; line cadence describes the operating context, not measured model latency.
Approach & contributions
Defined an image-sampling and annotation strategy combining representative data with negative cases, then iterated on labels as model evidence exposed gaps.
Developed RetinaNet detectors, analyzed errors by class, tuned class-specific thresholds and introduced semi-automatic out-of-time tests before validating deployed models on real production cases.
Focus: owning the learning loop from requirements and data quality to deployment evidence.
02 / 3D & geospatial systemsAI systems · Data automation
From heterogeneous data
to digital-twin pipelines.
Large-scale 3D and geospatial processing across LiDAR, terrain, buildings, OSM and satellite data, translating research methods into modular operational pipelines.
Multi-source3D, LiDAR, terrain, OSM and satellite data
Operationalmodular pipelines designed for scale and traceability
Approach & contributions
Developed distributed processing with Databricks, PySpark and Delta Lake, supported by PostgreSQL/PostGIS data layers and containerized Azure workloads.
Evaluated accuracy, compute-cost and processing-time trade-offs; introduced logging, metrics, traceability and reproducibility practices while collaborating with simulation, product and cloud teams.
Focus: systems thinking across data scale, technical trade-offs and the transition from research to engineering.
03 / Knowledge & agent systemsRAG · Agent automation
Designing knowledge workflows
around real decisions.
RAG and multi-agent prototypes for technical research, knowledge access and complex document workflows, connecting retrieval, orchestration, human feedback and deployment choices.
Modularreusable layers for interaction, orchestration, tools and data
Human-guidedfeedback and iterative review built into agent workflows
Technical choices were assessed against source quality, commercial-use constraints, context reliability and the needs of intended users.
Approach & contributions
Compared scientific and web search sources, document-indexing strategies, chunking approaches and lightweight multimodal options for retrieval systems.
Designed modular agent architectures, tested persistent memory and human-in-the-loop behavior, and explored Dockerized local-model deployment with Ollama.
Focus: moving from isolated demos toward reusable, governable AI components.
04 / Applied AI discoveryOpportunity framing · Prototyping
Choosing the right automation
for the workflow.
Framed three AI opportunities across technical training, document-quality checks and engineering assistance, moving each toward a demonstrator or clear technical direction.
3 workflowsneeds, constraints and adoption barriers analyzed with domain teams
Fit for purposesemantic search, deterministic rules or AI agents selected by need
Approach & contributions
Built a semantic-search knowledge assistant for technical training and presented the first demonstrator to domain experts.
Developed a deterministic PDF-validation prototype for technical publications and helped frame an AI-assisted engineering proof of concept.
Focus: validating usefulness with experts before expanding scope or committing to a technology.
05 / Medical imaging & GenAIAI R&D · Emerging solutions
Structuring emerging AI
into rigorous R&D.
Applied research and engineering for medical imaging and synthetic-data generation, from dataset and literature analysis to evaluation design and deployment considerations.
End to endfrom evidence and datasets to experimental pipelines
Decision-readyevaluation and maturity milestones made explicit
Approach & contributions
Designed end-to-end experimental pipelines and explored conditional generative approaches combining diffusion models and Gamma-VAE concepts.
Built agentic research assistants for scientific, market, funding and dataset discovery, while mentoring junior engineers and communicating results to technical and non-technical audiences.
Focus: turning emerging methods into structured engineering work with explicit evidence and maturity milestones.
06 / Multimodal computer vision researchResearch depth · Multimodal AI
Bringing geometry
and temperature together.
Dual-PhD research combining RGB, thermal imaging and 3D reconstruction for chronic wound monitoring, supported by deep learning and medical-image analysis.
RGB + thermalmultimodal information registered on 3D geometry
4,000+ imagesinternational clinical data collection coordinated
Research & publications
Designed the research and acquisition-to-visualization pipeline and published peer-reviewed results.
04 / Experience & direction
A broader scope.
The same problem-solving thread.
Quantitative foundations, research depth and applied engineering—now converging in AI systems and technical direction.
2023–Present
Applied Scientist / Senior Data Scientist · Expleo Group
Applied AI technical contributor and lead across R&D, innovation and industrial projects. Work spans problem framing, system design, hands-on prototypes, evaluation, deployment-oriented engineering and technical mentoring.
Current focus includes industrial computer vision, 3D and geospatial systems, medical imaging, GenAI, RAG, agents and workflow automation—with increasing responsibility for technical trade-offs and the transition toward usable systems.
See selected contributions2019–2023Dual PhD · 2023
3D computer vision & multimodal imaging
Doctoral work across computer science and engineering: combining 3D models, thermal imaging and deep learning for chronic wound assessment, while coordinating clinical data acquisition and supervising students.
Université d’Orléans · Pontificia Universidad Católica del Perú
Earlier experience2011–2018
Statistics, machine learning & decision support
Credit risk modeling, geospatial analysis and consulting. Building a foundation in quantitative reasoning, varied data sources and applied business problems.
Earlier roles
- Data Scientist — Credit Risk Modeling Specialist
LenddoEFL · March 2015–October 2018 - Geo-Intelligence Consulting Analyst
Business Analytics SAC · January 2014–March 2015 - Credit Risk Analyst
Entrepreneurial Finance Lab · September 2011–December 2013
05 / Capabilities
Tools follow
the problem.
Breadth is useful when it supports a better decision. I select and combine tools around the problem, evidence and system constraints.
AI & machine learning
Statistical ML · Computer vision · Deep learning · Multimodal AI · LLMs · RAG · Agents
Python / PyTorch / TensorFlow / OpenCV / Open3D
AI engineering
APIs · Evaluation pipelines · Workflow automation · Retrieval systems
FastAPI / Docker / GitLab CI/CD / CrewAI / LlamaIndex / ChromaDB / Ollama
Data & platforms
Relational and vector databases · Distributed and geospatial processing · Cloud and data platforms
SQL / PostgreSQL / PostGIS / Azure / Databricks / PySpark / Delta Lake / GeoPandas / QGIS / ArcGIS / AKS exposure
06 / Research & publications
Scientific depth.
Applied perspective.
My research background brings rigor to experimentation, model evaluation and the interpretation of results.
Education
Two disciplines.
A shared research question.
- PhD in Computer Science
- Université d’Orléans
- PhD in Engineering
- Pontificia Universidad Católica del Perú
- MSc in Statistics
- Pontificia Universidad Católica del Perú
- BSc in Statistical Engineering
- Universidad Nacional de Ingeniería, Peru
Computer vision · Deep learning
Multi-View Data Augmentation to Improve Wound Segmentation on 3D Surface Model by Deep Learning
Read publication Multimodal imagingMultimodal and Multiview Wound Monitoring with Mobile Devices
Read publication Thermal imaging · Clinical monitoringCorrection of Temperature Estimated from a Low-Cost Handheld Infrared Camera for Clinical Monitoring
Read publication
Evelyn GutierrezStatistics → AI → Systems
07 / About
I enjoy problems that require
both analysis and building.
I’m an Applied AI professional with more than a decade of experience across data, machine learning and AI. What has stayed constant throughout my career is a preference for complex problems that need to be understood, structured and turned into something useful.
I’ve worked across statistics, computer vision, 3D and geospatial systems, medical imaging, GenAI and agentic AI. Rather than defining myself by one technology, I tend to start from the problem, explore the trade-offs, and choose the approach that makes the most sense.
I enjoy staying hands-on—analysing data, prototyping and building systems—while also thinking about architecture, interfaces, scalability and how a solution can move beyond the first demo. I particularly like working at the intersection of AI, automation and complex technical systems.
Spanish · English · French
08 / Let’s connect
A complex AI problem?
Let’s find a way forward.
For conversations about applied AI, AI engineering and building useful systems.
Get in touch