Skip to content
View dtortosa's full-sized avatar
3 followers · 24 following

Achievements

Achievement: Pull SharkAchievement: Pair Extraordinaire

Achievements

Achievement: Pull SharkAchievement: Pair Extraordinaire

Highlights

  • Pro

Block or report dtortosa

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dtortosa/README.md

Diego Salazar Tortosa | AI/ML Scientist & Engineer

I bring scientific rigor to production AI systems. With 11+ years of experience handling complex datasets and building machine learning models, I design backend architectures and AI workflows built to run at scale.

🛠️ Tech Stack & Core Competencies

  • AI Engineering: LLM Applications, Production RAG Systems, AI Agents, LangChain, Framework-Free Execution Loops, Prompt Engineering, Structured Outputs (Pydantic), Vector Databases (pgvector, FAISS), LLM evals
  • Machine Learning & Evaluation: Deep Neural Networks, Tree-Based Ensembles (XGBoost, Random Forest), Ensemble Stacking, Bayesian Inference, Nested Cross-Validation, Hyperparameter Optimization, Explainable AI (XAI)
  • Infrastructure & Backend: FastAPI, PostgreSQL, Celery, Azure, Docker, Cloud Deployments, Workflow and Cluster Managers (Nextflow and Slurm), Git/GitHub Actions
  • Scientific Computing: Python, PySpark, Numpy, Pandas, R, Bash, Parallel and Distributed Processing

📈 Featured Architectures

  • Production Agent Workflows: Event-driven, containerized microservices for processing unstructured documents.
  • Distributed Scientific Pipelines: Parallel and distributed architectures built with PySpark and multiprocessing to handle hundreds of gigabytes of high-dimensional data.

Pinned Loading

  1. ai-business-intelligence-assistant ai-business-intelligence-assistant Public

    AI agent that combines sales data analytics (Pandas), document retrieval (FAISS RAG), and execution monitoring in a Streamlit dashboard.

    Jupyter Notebook

  2. hr-knowledge-rag-agent hr-knowledge-rag-agent Public

    RAG pipeline that chunks documents, stores them in a Chroma vector database, and adds web context for specific topics. Built with LangChain, Jinja2, and Gradio.

    Jupyter Notebook

  3. twitter-forex-ml-pipeline twitter-forex-ml-pipeline Public

    Machine learning pipeline that scrapes tweets (snscrape), builds sentiment indexes, and predicts the EUR/USD exchange rate.

    Jupyter Notebook

  4. novel-ml-framework-genetic-adaptation novel-ml-framework-genetic-adaptation Public

    ML framework that benchmarks deep learning and tree ensembles on 180 GB of data using Slurm HPC clusters, nested cross-validation, and explainable AI.

    Python

  5. genome-wide-analysis-trainability-australia genome-wide-analysis-trainability-australia Public

    Distributed genomic pipeline that processes a 3.85B-genotype matrix with PySpark and HPC, running multi-model polygenic scoring with 100-fold validation.

    Python

  6. novel-ml-method-climate-change-prediction novel-ml-method-climate-change-prediction Public

    Novel geospatial machine learning framework that runs 100k+ combinatorial scenario projections across IPCC climate pathways, using model ensembles and out-of-distribution validation.

    R