Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm Javier García, a software and data engineer focused on building AI-powered SOC log analysis pipelines. I design and deploy end-to-end systems using LLMs, FAISS, RAG, and ETL pipelines to transform raw logs into actionable insights. I enjoy backend and data-intensive applications and love turning complex problems into reliable, scalable systems. Currently I’m an R&D AI Engineer intern at S2 Group, working on LLM-based pipelines, retrieval systems, and evaluation workflows to boost model performance and reduce errors. I’m excited by backend architectures, data engineering, and applied AI, and I’m eager to contribute to AI-driven SOC analytics.…I'm Javier García, a software and data engineer focused on building AI-powered SOC log analysis pipelines. I design and deploy end-to-end systems using LLMs, FAISS, RAG, and ETL pipelines to transform raw logs into actionable insights. I enjoy backend and data-intensive applications and love turning complex problems into reliable, scalable systems. Currently I’m an R&D AI Engineer intern at S2 Group, working on LLM-based pipelines, retrieval systems, and evaluation workflows to boost model performance and reduce errors. I’m excited by backend architectures, data engineering, and applied AI, and I’m eager to contribute to AI-driven SOC analytics.

Javier García

AI Engineer, Data Scientist, Programmer, +5





I'm Javier García, a software and data engineer focused on building AI-powered SOC log analysis pipelines. I design and deploy end-to-end systems using LLMs, FAISS, RAG, and ETL pipelines to transform raw logs into actionable insights. I enjoy backend and data-intensive applications and love turning complex problems into reliable, scalable systems. Currently I’m an R&D AI Engineer intern at S2 Group, working on LLM-based pipelines, retrieval systems, and evaluation workflows to boost model performance and reduce errors. I’m excited by backend architectures, data engineering, and applied AI, and I’m eager to contribute to AI-driven SOC analytics.…I'm Javier García, a software and data engineer focused on building AI-powered SOC log analysis pipelines. I design and deploy end-to-end systems using LLMs, FAISS, RAG, and ETL pipelines to transform raw logs into actionable insights. I enjoy backend and data-intensive applications and love turning complex problems into reliable, scalable systems. Currently I’m an R&D AI Engineer intern at S2 Group, working on LLM-based pipelines, retrieval systems, and evaluation workflows to boost model performance and reduce errors. I’m excited by backend architectures, data engineering, and applied AI, and I’m eager to contribute to AI-driven SOC analytics.

Available to hire

I’m Javier García, a software and data engineer focused on building AI-powered SOC log analysis pipelines. I design and deploy end-to-end systems using LLMs, FAISS, RAG, and ETL pipelines to transform raw logs into actionable insights. I enjoy backend and data-intensive applications and love turning complex problems into reliable, scalable systems.

Currently I’m an R&D AI Engineer intern at S2 Group, working on LLM-based pipelines, retrieval systems, and evaluation workflows to boost model performance and reduce errors. I’m excited by backend architectures, data engineering, and applied AI, and I’m eager to contribute to AI-driven SOC analytics.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Spanish; Castilian

Fluent

Norwegian

Intermediate

Work Experience

Software & Data Engineer Internship at S2 Group

October 1, 2025 - Present

Built LLM-based pipelines for SOC alert triage using RAG and structured outputs. Developed retrieval systems with embeddings, FAISS and custom chunking strategies. Designed ETL pipelines for logging, ingestion (CSV -> processing -> database). Implemented evaluation workflows to improve LLM performance and reduce errors.

Intern, AI Engineer - S2 Group at S2 Group

October 1, 2025 - Present

Built LLM-based pipelines for SOC alert triage using retrieval-augmented generation and structured outputs. Developed retrieval systems with embeddings, FAISS and custom chunking strategies. Designed ETL pipelines for log ingestion (CSV → processing → database). Implemented evaluation workflows to improve LLM performance and reduce errors.