Alejandro de la Fuente

Skills and education

Every chip names a skill demonstrated on this site. Behind the skills sits the education record: degrees in biology and quantitative ecology, and the certificates that retrained me for AI engineering.

Skills

Builds with Python RAG pipelines Knowledge graphs LLM-as-judge evaluation SQL Grounded in Bayesian inference Hierarchical models Uncertainty quantification Evaluation design R

My core strength is statistical modelling under uncertainty: Bayesian hierarchical methods applied to noisy, sparse and structured data. The same discipline now runs my AI engineering: retrieval-augmented generation (RAG) pipelines, agents and the evaluation that proves they work. Research added the habits that transfer: measurement design first, explicit assumptions, delivery under real constraints and writing that can be audited.

What I deliver

Depth, by area

Stack
  • AI and language models
    • OpenAI, Anthropic and Google APIs, and open models on Hugging Face
    • LangChain, LangGraph, LlamaIndex, LiteLLM
    • ChromaDB, Neo4j and Cypher
    • Model Context Protocol (MCP) servers and clients with FastMCP
    • TruLens and Arize Phoenix for tracing and evaluation
    • Gradio, Streamlit and Modal for delivery
  • Machine learning and data
    • Python: pandas, NumPy, scikit-learn, XGBoost, TensorFlow, PyTorch
    • SQL on PostgreSQL
    • R and the tidyverse
    • Git and GitHub
  • Methods
    • Bayesian and hierarchical modelling, spatiotemporal forecasting
    • Supervised and unsupervised learning, embeddings and semantic search
    • Knowledge graphs and graph-backed retrieval
    • Ranking, A/B testing and causal framing
Bayesian and hierarchical modelling
  • Generalised linear, additive and mixed models with partial pooling
  • Priors as explicit assumptions, uncertainty propagated into every forecast
  • Observation separated from process: N-mixture and integrated population models
  • Spatiotemporal structure, species distribution models and threshold inference
Language models and agents
  • Prompting for structured outputs, with schema contracts and bounded retries
  • RAG: embeddings, vector stores, sentence-window and auto-merging retrieval
  • RAG evaluation: context relevance, groundedness and answer relevance
  • Agent workflows: planning loops, tool calling and human-in-the-loop checkpoints
  • Agent evaluation: router, skill and trajectory scoring over traced experiments
  • Judge model design, benchmarked against labelled data
  • Knowledge graph construction and retrieval with Neo4j and Cypher
  • Fine-tuning: supervised frontier fine-tuning and QLoRA on open models
  • Guardrails and observability: cross-family review models, per-turn logging, drift detection
Machine learning and evaluation
  • Supervised learning: regression, tree ensembles and gradient boosting
  • Unsupervised learning: clustering, dimensionality reduction, anomaly detection
  • Deep learning: training fundamentals in TensorFlow, Keras and PyTorch
  • Validation design: cross-validation, temporal splits, leakage checks, calibration
  • Interpretability: feature importance, partial dependence, SHAP explanations
  • Experimentation: A/B testing, causal framing, decisions under uncertainty
Data and software engineering
  • Ingestion and transformation with schema discipline and reliable input and output
  • Analytical SQL: joins, window functions, common table expressions, reusable views
  • Reproducibility: pinned environments, deterministic runs, versioned artefacts
  • Quality controls: input validation, unit tests, docstrings and type hints
  • Geospatial pipelines: raster and vector workflows, spatial feature engineering
  • Visualisation and small apps: matplotlib, plotly, ggplot2, Gradio, Streamlit, Shiny
Field and modelling skills
  • Animal trapping
  • Modelling
    • Population dynamics
    • Biophysical models
    • Occupancy
    • Species distribution
    • Landscape ecology
    • Movement
    • Climatic data and other time-series
    • Spatial analysis
  • Stats
    • Frequentist
    • Bayesian
  • Coding
    • R
    • WinBUGS
    • Python
    • SQL
  • AI
    • Prompt engineering
    • Agentic AI
  • Languages
    • Spanish, first language
    • English, IELTS 7.0
    • French, basic

Education

Certificates and training

Bayesian and hierarchical modelling

R

  • R for Data Science
  • Statistics in R workshop, Dr Murray Logan (AIMS). Covers tidyverse, ggplot2, R Markdown, linear models, GLMs and GLMMs, mixed-effects models and multivariate analyses.

Python and machine learning

  • The Complete Python Bootcamp: From Zero to Hero in Python (certificate). Covers core Python, data structures, OOP, error handling, file work and web scraping with Requests and BeautifulSoup.
  • Python for Data Science and Machine Learning Bootcamp (certificate). Covers pandas, NumPy, Matplotlib, Seaborn, Plotly and scikit-learn: regression, trees, random forests, SVM, k-NN, K-Means, PCA, intro NLP and deep learning with Keras and TensorFlow.
  • Machine Learning Specialisation, DeepLearning.AI, Andrew Ng (certificate). Covers supervised learning, advanced learning algorithms, unsupervised learning, anomaly detection, recommenders and introductory reinforcement learning. Module certificates: supervised learning, advanced algorithms, unsupervised learning.

SQL and databases

  • The Complete SQL Bootcamp: PostgreSQL & pgAdmin (certificate). Covers querying, aggregation, joins, schema fundamentals and pgAdmin tooling.
  • SQL for Data Analysis: Advanced SQL Querying Techniques (certificate). Covers subqueries, CTEs, window functions, NULL-safe handling and reusable views.

AI engineering

  • AI Engineer Core Track: LLM Engineering, RAG, QLoRA, Agents (certificate). Covers frontier APIs, open-source models, RAG, frontier and QLoRA fine-tuning, and agent deployment with LangChain and Gradio.
  • ChatGPT Prompt Engineering for Developers (certificate). Covers structured prompting, iterative refinement and the OpenAI API.
  • Agentic AI, Andrew Ng (certificate). Covers task decomposition, reflection, tool calling and multi-agent coordination.
  • AI Agents in LangGraph (certificate). Covers graph-structured agent workflows, state, tracing and human-in-the-loop checkpoints.
  • Evaluating AI Agents, DeepLearning.AI (Arize AI) (certificate). Covers agent decomposition, tracing with Arize Phoenix, router, skill and trajectory evaluations, judge design and production monitoring.
  • Building and Evaluating Advanced RAG, DeepLearning.AI (LlamaIndex, TruEra) (certificate). Covers the RAG triad with TruLens, sentence-window and auto-merging retrieval, and evaluation-driven iteration.
  • Knowledge Graphs for RAG, DeepLearning.AI (Neo4j) (certificate). Covers Cypher, vector search over graph data and graph-backed question answering.
  • Agentic Knowledge Graph Construction, DeepLearning.AI (Neo4j) (certificate). Covers multi-agent schema inference and knowledge graph construction with Google’s Agent Development Kit.
  • Claude Code: A Highly Agentic Coding Assistant, Anthropic (certificate). Covers agentic coding workflows, context discipline, subagents, git worktrees, hooks and MCP servers.
  • Agent Skills with Anthropic (certificate). Covers skill design and packaging, progressive disclosure, and skills with the Claude API and the Claude Agent SDK.
  • MCP: Build Rich-Context AI Apps with Anthropic (certificate). Covers MCP servers and clients with FastMCP, reference servers and remote deployment.

Version control

  • The Git & GitHub Bootcamp (certificate). Covers branching, merging, rebasing, recovery workflows and GitHub collaboration.

Cloud

  • AWS Certified Cloud Practitioner, CLF-C02 (certificate). Covers core AWS services, IAM, networking, monitoring and cost governance at a conceptual level.