AI / ML Engineer - Intelligence Systems

Turn data
into instinct.

I build machine-learning systems that learn from messy signals, become useful in production, and create decisions people can trust, from retrieval and forecasting to evaluation and inference.

Models shipped 38 production + research systems
Inference reliability 96% monitored uptime
Open to selective work
Current focus

Applied AI, LLM evaluation, retrieval systems, forecasting and ML platforms.

02 / Model craft

Four ways I make
models useful.

Representation learning Embeddings, transformers, multimodal features and semantic structure.
Retrieval + generation Grounded context pipelines with ranking, chunking, evaluation and guardrails.
Evaluation systems Offline metrics, human feedback loops, regression suites and quality gates.
Production inference Latency-aware serving, observability, batch and online tradeoffs, iteration.
Featured system
RAG

Context Engine

Retrieval, structured signals and evaluation gates for support intelligence, designed to make answers more grounded and measurable.

-31% resolution time
03 / Build loop

From hypothesis
to healthy inference.

01

Frame

Define the decision, failure modes, data boundaries and success metric.

02

Learn

Prototype representations, baselines and model behavior against real examples.

03

Stress

Probe edge cases, drift, hallucination, latency and regression risk.

04

Ship

Deploy with observability, evaluation gates and a feedback loop for iteration.

04 / Selected work

Small systems,
large signal.

02 · Forecasting

Demand Pulse

Probabilistic forecasting pipeline with rolling backtests and confidence-aware alerts.

Time seriesPython
03 · NLP

Intent Atlas

Semantic intent layer that clusters support language into actionable operational themes.

NLPClustering
05 / Contact

Have a signal
worth exploring?

For applied AI projects, ML platform work, research collaborations or thoughtful product conversations, send a note.

✉ elena@example.com
◈ Barcelona, Spain