Skip to content
View nepryoon's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report nepryoon

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
nepryoon/README.md

Hi, I'm Luca Lillo πŸ‘‹

Machine Learning Engineer | Data Scientist | MLOps & Production ML | GenAI (RAG/LLMOps)

I build production-grade ML systems end-to-endβ€”from data pipelines and feature engineering to model training and deployment-ready inference services. My focus is on measurable outcomes, reproducibility, and operational excellence.


πŸš€ What I Do

  • πŸ”¬ End-to-End ML Engineering: Data pipelines β†’ Feature engineering β†’ Model training/validation β†’ Production deployment
  • πŸ€– GenAI & LLMOps: RAG systems with retrieval + reranking, evaluation harnesses, prompt engineering, and auditable outputs
  • βš™οΈ MLOps & Platform Engineering: CI/CD, Docker/Kubernetes, monitoring, model versioning (MLflow, DVC), and infrastructure as code
  • πŸ“Š Data Engineering: PostgreSQL, ETL/ELT, data quality frameworks, and dataset curation
  • ☁️ Cloud & Infrastructure: AWS (ECS, ECR, ALB), Terraform, Kubernetes deployment patterns

πŸ’Ό Currently

  • πŸ—οΈ Founder & Lead AI Engineer at Neuromorphic Inference Lab (Open Source Initiative)

    • Building production RAG services with citation/audit trails and regression-style evaluation harnesses
    • Deploying ML systems to AWS with CI/CD quality gates and operational telemetry
    • Improving data processing efficiency by 30% through optimized ETL and reproducible builds
  • ⚑ Technical Operations Lead at E-Distribuzione S.p.A. (Enel Group)

    • Operationalizing predictive analytics for grid operations (LV/MV fault detection)
    • Sustaining 99.9% operational uptime through robust batch inference workflows
    • Leading technical teams and establishing execution cadences for operational stability

πŸ› οΈ Tech Stack

Languages
Python
JavaScript
TypeScript
SQL
Bash

ML/AI
PyTorch
TensorFlow
scikit-learn
MLflow

MLOps & Infrastructure
Docker
Kubernetes
AWS
Terraform
GitHub Actions
FastAPI


πŸŽ“ Education

  • πŸŽ“ MSc, Data Science and Artificial Intelligence – University of Liverpool (exp. Aug 2027)
  • πŸŽ“ Postgraduate Certificate, Data Science and AI – University of Liverpool (May 2026)
  • πŸŽ“ MSc, Management and Innovation – Mercatorum University (Dec 2024)
  • πŸŽ“ BSc, Psychological Sciences and Techniques – Mercatorum University (Feb 2023)

πŸ“œ Certifications

βœ… Full-Stack Software Developer (IBM) – Jan 2026
βœ… Python (Kaggle) – Aug 2025
πŸ”„ AWS Certified Machine Learning Engineer - Associate (MLA-C01) – In Progress
πŸ”„ Google Professional Machine Learning Engineer – In Progress
πŸ”„ AWS Certified Data Engineer - Associate (DEA-C01) – In Progress
πŸ”„ Certified Kubernetes Administrator (CKA) – In Progress
πŸ”„ HashiCorp Certified: Terraform Associate – In Progress


πŸ† Recognition

πŸ₯‡ Innovation Challenge Winner – Enel (Feb 2017)
Awarded for proposing an AR-enabled smart helmet solution to monitor subcontractor work quality and enhance operational safety compliance.


🌱 Beyond Code

  • 🌍 Former City Coordinator at Plastic Free – coordinating volunteer-led environmental clean-up initiatives and mobilizing community participation
  • πŸ“š Continuous learner with a bias for systems thinking, operational rigor, and engineering excellence

πŸ“« Let's Connect

LinkedIn
Portfolio
GitHub


⚑ "Strong bias for measurable outcomes, reproducibility, and operational excellence."

Pinned Loading

  1. neuromorphic-inference-lab-site neuromorphic-inference-lab-site Public

    Cloudflare Pages portfolio: systems hub + proof ledger + build provenance (Pages Functions).

    HCL

  2. edgepulse edgepulse Public

    Production patterns for ML/AI systems: APIs, infra, tracing, and deployment-ready templates.

    TypeScript 1

  3. mv-grid-fault-risk mv-grid-fault-risk Public

    End-to-end MV grid fault risk scoring: feature engineering, tracked training, artefact versioning, API serving, monitoring-ready outputs

    Python

  4. nil-forecast-studio nil-forecast-studio Public

    Forecasting system with data validation, backtesting, reproducibility, and artefacts suitable for stakeholders.

  5. nil-rag-copilot nil-rag-copilot Public

    RAG Knowledge Copilot with retrieval tracing, citations, guardrails, and an evaluation harness for regression testing.

    Python

  6. nil-tabular-risk nil-tabular-risk Public

    Tabular risk modelling with reproducible pipelines, evaluation, and deployment-friendly structure.