Lead AI Platform Engineer — Full-Stack & LLM Systems

Peak3 (formerly ZA Tech); Madrid; Presencial; EUR 90.000 - 130.000; Jornada completa

Descripción de la vacante

Peak3 is hiring a Principal AI Full-Stack Engineer to own the design, build, and operation of agentic AI systems powering core insurance products. You will architect LLM inference chains, build production AI infrastructure, and ship full-stack features from model to UI.

You should be comfortable debugging production RAG recalls and collaborating with actuarial and underwriting teams to create explainable, auditable AI systems. The role spans frontend, backend, and cloud deployments.

Formación

• Experience shipping production software at scale, including LLM/AI systems.
• Proficient in Python or TypeScript and a modern frontend framework.
• Hands-on LLM engineering depth: RAG/retrieval, function calling, agent frameworks.
• Solid AI infra grounding: vector databases, embedding models, model serving.
• Strong product instincts and ability to translate ambiguous problems into scoped solutions.
• Experience taking an LLM system from prototype to production with real users and operational load.

Responsabilidades

• Build agentic AI applications end-to-end — RAG pipelines, multi-agent orchestration, tool calling, workflows.
• Design and optimize LLM inference chains: prompts, outputs, fine-tuning, evals, observability.
• Stand up production-grade AI infrastructure: vector DBs, model gateways, inference optimization.
• Own full-stack delivery — frontend (React/Next.js), backend (Python/TypeScript), cloud-native deployment (K8s/Serverless).
• Partner with actuarial, underwriting, and claims teams to build trustworthy, auditable AI systems.

Conocimientos

Python

TypeScript

Frontend framework

LLM engineering

AI infra

Kubernetes

Problem solving

Open-source

Herramientas

LangGraph

LlamaIndex

Vector databases

Model deployment

Descripción del empleo

Peak3 is hiring a Principal AI Full-Stack Engineer to own the design, build, and operation of agentic AI systems powering core insurance products. You will architect LLM inference chains, build production AI infrastructure, and ship full-stack features from model to UI.

You should be comfortable debugging production RAG recalls and collaborating with actuarial and underwriting teams to create explainable, auditable AI systems. The role spans frontend, backend, and cloud deployments.