Freelance ML Engineers in SpainFreelance ML Engineers in Spain
ProjectsPeople
Andrés Lage's avatar
Andrés Lage
proFerrol, Spain
Independent AI Architect&Strategist EU AI ACT&OWASP
New to Contra
Independent AI Architect&Strategist EU AI ACT&OWASP
Cover image for Industrial AI replaces opaque, high-cost
Industrial AI replaces opaque, high-cost LLMs with deterministic, hybrid architectures built specifically for high-risk, heavily regulated enterprise environments. It leverages glass-box explainability (like EBMs) and cascading NLP pipelines to resolve up to 80% of operational traffic at zero token cost and sub-millisecond latency on CPU. By embedding continuous statistical drift monitoring (KS-test/PSI), it translates raw telemetry into audit-ready assets, guaranteeing strict compliance with the EU AI Act and ISO 42001.
1
15
Cover image for Most ML projects that win
Most ML projects that win Kaggle would not survive a regulatory audit in 2026. This one is built specifically to do both competitive performance AND audit-ready by design. Insurance claim prediction (Porto Seguro dataset, 3.6% positive class, highly imbalanced) implemented end-to-end with EU AI Act, Solvency II and ISO 42001 compliance as the architectural starting point not as a documentation afterthought. Four pillars: MLOps & Shadow Monitor Architecture. Vendor-agnostic monitoring layer that reads inference logs independently from the production model (Azure ML / SageMaker / Vertex AI). KS-test drift detection in real time. Zero vendor lock-in. The Shadow Monitor is the answer to "how do you audit a black-box cloud ML service?" Explainability vs Performance trade-off, decided with evidence. EBM (Explainable Boosting Machine) chosen over XGBoost/LightGBM. ROC-AUC 0.608 vs 0.64-0.65 for XGBoost a 4% performance cost in exchange for native glass-box explainability that regulators accept without SHAP post-hoc workarounds. The right call for regulated industries, the wrong call for tech. Threshold optimization on imbalanced data. Default scikit-learn 0.5 threshold yields F1 ≈ 0 on this dataset a model that "performs at 96.4% accuracy" is in fact useless. Custom F1-Score curve finds the optimal decision boundary at 0.091. The difference between a Kaggle submission and a production system. Automated Compliance Dashboard. Fairness (demographic parity, equalized odds, protected-attribute analysis), Transparency (feature-level contributions, full documentation), Accountability (model card, ADRs, governance framework, human-in-the-loop). Maps directly to EU AI Act high-risk requirements, Solvency II model validation, and ISO 42001 controls. Why Polars over Pandas? Built in Rust, 5-12x faster, lazy evaluation, native multi-threading. For production ML under EU AI Act, processing speed on inference logs is not a nice-to-have it's an audit requirement. Template replicable for banks, insurers, healthcare, and any organization where ML decisions need to defend themselves in front of a regulator.
0
32
Cover image for This production-ready Hotel Voice Assistant
This production-ready Hotel Voice Assistant integrates Google Gemini 2.0 with a scalable Flask/Waitress backend to power fluid, context-aware conversational booking experiences in Spanish. It leverages a distributed Redis session store for stateful multi-turn memory, backed by native Function Calling to stream live availability and real-time pricing directly from the Amadeus GDS API. Engineered with an "auditability-by-design" framework, the architecture implements pluggable callback hooks and strictly aligns with the OWASP Agentic Top 10 (2026) to mitigate multi-agent risks and secure user data.
1
25
Cover image for Production-ready multi-agent system demonstrating Agentic
Production-ready multi-agent system demonstrating Agentic AI principles. Built with LangGraph for workflow orchestration, FastAPI for the API, and OpenAI GPT-4. Features autonomous decision-making, tool use, and multi-agent collaboration for intelligent data analysis and strategic recommendations.
0
32
ML Engineer(2)
Miguel J. Garrido's avatar
Miguel J. Garrido
Esplugues de Llobregat, Spain
AI & Data Solutions with Perfectionist Passion
AI & Data Solutions with Perfectionist Passion
Cover image for Digit Recognition with ML
Digit Recognition with ML
0
8
Cover image for LANGUAGE TRANSLATION USING SEQ2SEQ LEARNING
LANGUAGE TRANSLATION USING SEQ2SEQ LEARNING
0
5
Cover image for Movie Retrieval System using NLP Models
Movie Retrieval System using NLP Models
0
8
Placeholder project card media
View more →
ML Engineer(2)
Ismael Charpentier's avatar
Ismael Charpentier
Granada, Spain
Data Scientist & ML Engineer | Python & Visualization Expert
Data Scientist & ML Engineer | Python & Visualization Expert
Cover image for Hopefield Neural Network
Hopefield Neural Network
0
10
Cover image for Solar System Formation Simulation
Solar System Formation Simulation
1
10
Cover image for World Happiness Dashboard
World Happiness Dashboard
1
26
Placeholder project card media
View more →
ML Engineer(1)
Mykyta Terentiev's avatar
Mykyta Terentiev
08740 Sant Andreu de la Barca, Spain
AI/ML Engineer | Building Scalable, Data-Driven Solutions
AI/ML Engineer | Building Scalable, Data-Driven Solutions
Cover image for Transaction Enrichment API | Elevate Banking Data | Snowdrop
Transaction Enrichment API | Elevate Banking Data | Snowdrop
0
1
Cover image for RBF-SVM Brand Verification Model
RBF-SVM Brand Verification Model
0
1
Cover image for Top IT Companies - Rankings & Reviews
Top IT Companies - Rankings & Reviews
0
1
Placeholder project card media
View more →
ML Engineer(2)
Luke Jovanovic's avatar
Luke Jovanovic
Madrid, Spain
agencra.xyz - Automated Pipelines. Ship in days, not weeks.
$5k+
Earned
27x
Hired
5.0
Rating
4
Followers
REPLIT_EXPERT

Expert

agencra.xyz - Automated Pipelines. Ship in days, not weeks.
Cover image for Alephyr — Trading Engine with Evolutionary Optimization
Alephyr — Trading Engine with Evolutionary Optimization
0
3
Cover image for Concordium — Supply Chain &
Concordium — Supply Chain & Testnet Infrastructure We delivered two blockchain projects for Concordium: a supply chain track-and-trace system and a testnet faucet. Track-and-trace: - Built a CIS-3 NFT smart contract (Rust) for product tracking. - Added sponsored transactions so users don’t need to hold tokens. - Implemented an indexer to track all on-chain movements in real time. - Shipped a full frontend and Docker-based infrastructure. Testnet faucet: - Developed a Next.js faucet with Cloudflare Turnstile bot protection. - Added per-address daily limits and balance checks via the explorer API. - Provided complete documentation for deployment and maintenance. Outcome: - Both systems production-ready and actively used. - 92 combined commits, clean architecture, ready-to-reuse patterns. This case shows our ability to ship end-to-end blockchain solutions—smart contracts, infrastructure, and UX—in one go.
1
45
Cover image for Yield-Nexus — Real-Time Crypto Portfolio
Yield-Nexus — Real-Time Crypto Portfolio & Trading Platform We built Yield-Nexus as a real-time crypto portfolio and trading dashboard aggregating data across Binance and Bybit. Traders needed a unified view of spot holdings, futures positions, and PnL without switching between exchange consoles.
1
38
Cover image for NYC Watch Party Finder — From Idea to Production in 3 Days
NYC Watch Party Finder — From Idea to Production in 3 Days
0
0
ML Engineer(1)