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

Hi, I’m Adrián Carbonell Sánchez, an AI and software engineer focused on shipping production-grade LLM pipelines, multi-agent systems, and on-device inference. I enjoy turning complex research ideas into robust, scalable solutions that work in both cloud and edge environments, with a track record of reducing latency and enabling rapid product iterations. I’ve built RAG-enabled backends, integrated LLMs with document indexes and vector stores, and led cross-functional collaboration with frontend, DevOps, and data teams to deploy AI features across fleets and markets. I’m passionate about observability, safety, and delivering reliable AI experiences that business teams can trust.…Hi, I’m Adrián Carbonell Sánchez, an AI and software engineer focused on shipping production-grade LLM pipelines, multi-agent systems, and on-device inference. I enjoy turning complex research ideas into robust, scalable solutions that work in both cloud and edge environments, with a track record of reducing latency and enabling rapid product iterations. I’ve built RAG-enabled backends, integrated LLMs with document indexes and vector stores, and led cross-functional collaboration with frontend, DevOps, and data teams to deploy AI features across fleets and markets. I’m passionate about observability, safety, and delivering reliable AI experiences that business teams can trust.

Adrián Carbonell Sánchez

AI Engineer, Full Stack Developer, Web Developer, +1





Hi, I’m Adrián Carbonell Sánchez, an AI and software engineer focused on shipping production-grade LLM pipelines, multi-agent systems, and on-device inference. I enjoy turning complex research ideas into robust, scalable solutions that work in both cloud and edge environments, with a track record of reducing latency and enabling rapid product iterations. I’ve built RAG-enabled backends, integrated LLMs with document indexes and vector stores, and led cross-functional collaboration with frontend, DevOps, and data teams to deploy AI features across fleets and markets. I’m passionate about observability, safety, and delivering reliable AI experiences that business teams can trust.…Hi, I’m Adrián Carbonell Sánchez, an AI and software engineer focused on shipping production-grade LLM pipelines, multi-agent systems, and on-device inference. I enjoy turning complex research ideas into robust, scalable solutions that work in both cloud and edge environments, with a track record of reducing latency and enabling rapid product iterations. I’ve built RAG-enabled backends, integrated LLMs with document indexes and vector stores, and led cross-functional collaboration with frontend, DevOps, and data teams to deploy AI features across fleets and markets. I’m passionate about observability, safety, and delivering reliable AI experiences that business teams can trust.

Available to hire

Hi, I’m Adrián Carbonell Sánchez, an AI and software engineer focused on shipping production-grade LLM pipelines, multi-agent systems, and on-device inference. I enjoy turning complex research ideas into robust, scalable solutions that work in both cloud and edge environments, with a track record of reducing latency and enabling rapid product iterations.

I’ve built RAG-enabled backends, integrated LLMs with document indexes and vector stores, and led cross-functional collaboration with frontend, DevOps, and data teams to deploy AI features across fleets and markets. I’m passionate about observability, safety, and delivering reliable AI experiences that business teams can trust.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

Spanish; Castilian

Fluent

English

Advanced

Swedish

Intermediate

Catalan; Valencian

Advanced

Work Experience

AI Engineer at Unnamed Start-up

October 1, 2025 - Present

Designed and integrated multi-agent LLM workflows into backend services using Python and Go. Implemented vector database retriever pipelines to support production RAG features. Built AWS-based ingestion pipelines for document indexing and embedding generation. Collaborated with frontend and DevOps teams to deploy and integrate AI services into the product. Recruited by my previous manager following mass layoffs.

Software Engineer at ZEEKR Tech EU

September 1, 2023 - November 1, 2025

Integrated an LLM-powered voice assistant with RAG into vehicle backend, enabling natural-language vehicle commands. Deployed to a large subset of the fleet and implemented a low-latency streaming pipeline (wake-word → ASR → LLM response → TTS) achieving end-to-end latency around 2s (p95). Implemented RAG using Azure AI Search with vector embeddings and backend orchestration for command execution, including intent detection and safety validation. Established observability with telemetry for usage, uptime, and ML ops metrics, dashboards, and alerts.

Full-Stack Engineer at Microcement PRO

March 1, 2023 - September 1, 2023

Integrated AI-powered document search using RAG into internal business workflows. Built a full-stack application with React frontend, backend APIs, PostgreSQL, and vector-based retrieval. Maintained client communications to ensure timely delivery and alignment with requirements.

Software Engineer Intern at Unit 4

July 1, 2022 - December 31, 2022

Developed an AI system to aid breast cancer diagnosis, training a custom computer-vision model on a curated dataset and building a clinician-facing UI for image upload and classifications. Set up a Retrieval-Augmented Generation (RAG) system in Azure to enable the LLM to answer domain-specific questions by indexing documents. Worked in an international team emphasizing Agile practices, TDD, and peer programming.

AI Engineer at Unnamed Startup

October 1, 2025 - Present

Designed and integrated multi-agent LLM workflows into backend services; built vector-database retrieval pipelines to support production RAG features; created AWS-based ingestion and indexing pipelines for documents and embeddings; collaborated with frontend and DevOps to deploy AI services into the product; recruited into the role following a prior team layoff.

Software Engineer at ZEEKR Tech EU (CTEVT)

September 1, 2023 - November 1, 2025

Integrated an LLM-powered voice assistant with Retrieval-Augmented Generation (RAG) into the vehicle backend, enabling natural-language vehicle commands; deployed to ~90% of the fleet with ~40% 30-day retention. Built a low-latency streaming pipeline: wake-word → ASR → LLM response → TTS; end-to-end p95 latency: 2s. Implemented RAG using Azure AI Search (vector embeddings) and backend orchestration, including intent detection and safety validation. Instrumented OpenTelemetry for usage, uptime, and LLM/MLOps metrics; dashboards and alerts. Tech: Azure OpenAI, Azure Speech (ASR/TTS), Azure AI Search, Golang, Docker, Terraform, OpenTelemetry, Grafana.

Software Engineer Intern at Unit4

July 1, 2022 - December 1, 2022

Contributed to an AI system project to aid breast cancer diagnosis, including data preparation and model training; built a user interface allowing professionals to upload images and receive classifications. Implemented a Retrieval-Augmented Generation (RAG) system on Azure, with logging and monitoring. Developed an internal tooling stack and integrated with Azure DevOps.