ML Engineer Practitioner building RAG systems, agentic workflows, and end-to-end ML pipelines.
Georgia Tech OMSCS (ML specialization) Β· 2 years production SWE at JPMorgan Β· Bilingual EN/ES
Ask my TwinBot about my projects, skills, or experience.
π Modular RAG
Production-oriented RAG framework. Hybrid retrieval (BM25 + FAISS + RRF + MMR), explicit wiring, observability-first. Computation and control separated by design.
π½οΈ Plate2Recipe
Multimodal pipeline: ViT ingredient recognition β GPT-2/LSTM recipe generation.
Key finding: lower training loss (100k samples) produced worse outputs than a smaller, better-tuned run (10k samples) β quality β loss.
π HireSignal
Schema-first job posting extraction pipeline β two LLM calls, everything else deterministic Python.
Pydantic-enforced structured extraction, Jinja2 rendering, QA audit gate, alias-aware skill match scoring, and a SQLite job tracker. Handles employment, freelance, and internship postings. Streamlit UI + CLI.
π Currently working on: adding retrieval evaluation (Hits@k, MRR) to Modular-RAG
π¬ Ask me about: RAG system design Β· hybrid retrieval Β· reliable agentic pipelines
π« Reach me: cordova.nellie@outlook.com.com Β· LinkedIn
π Portfolio: cordovank.github.io
π Resume: ML Engineer
π Open to: ML Engineer Β· AI Engineer Β· LLM Engineer roles