Ai Platform Engineer

Peak3 (Formerly Za Tech); Alcobendas; Presencial; EUR 60.000 - 100.000; Jornada completa

Descripción de la vacante

Peak3 busca un Ingeniero/a de Plataforma AI para unirse al equipo de AI Platform. Construirás y operarás infraestructuras que mantienen nuestros sistemas AI rápidos, fiables y rentables en producción, trabajando con el Ingeniero Full-Stack Principal para convertir decisiones en infraestructura sólida.

Trabajarás con bases de vectores, gateways de modelos e pipelines de inferencia, asegurando observabilidad, latencia y coste.

Formación

• Experiencia sólida en Python o TypeScript y despliegues en la nube (K8s o serverless).
• Conocimiento práctico de bases de datos vectoriales y modelos de embeddings.
• Experiencia con optimización de inferencia de LLM, cachés y herramientas de observabilidad.

Responsabilidades

• Construir y mantener la infraestructura AI central: bases de vectores, recuperación semántica, gateways de modelos y pipelines de inferencia.
• Implementar optimización de inferencia y caching para mantener latencia y coste.
• Configurar y mantener la observabilidad de sistemas LLM: logging, tracing, evals y monitorización de costes.
• Soportar incidencias de producción y on-call para sistemas AI, con runbooks y postmortems.
• Colaborar con el ingeniero Principal AI Full-Stack para implementar decisiones de arquitectura.

Conocimientos

Python

TypeScript

Backend infrastructure

Kubernetes

Serverless

Vector databases

Embedding models

LLM inference

Observability

On-call

Herramientas

LangGraph

LlamaIndex

Descripción del empleo

Descripción del trabajo

About Peak3

Peak3 is an award-winning vertical SaaS provider, enabling more relevant, convenient, and affordable insurance protection for everyone through our technology and ingenuity. Together with our clients, we create a more resilient and innovative future.

We combine insurance core, distribution, and AI solutions to deliver a step change in performance for insurers, MGAs, and insurance intermediaries. From greenfield embedded insurance ventures to multi-country core modernization programs, our SaaS solutions power top customers across life, health, and P&C insurance.

Our 500+ colleagues are based across over 15 countries in Europe, Asia and the Middle East - with an ambitious roadmap to scale further.

About the Role

As an AI Platform Engineer on the AI Platform team, youll build and operate the infrastructure that keeps our agentic AI systems fast, reliable, and cost-effective in production. Working closely with our Principal AI Full-Stack Engineer, youll take architectural direction and turn it into solid, well-monitored infrastructure - vector databases, model gateways, inference pipelines - that the rest of the team builds on.

Responsibilities

• Build and maintain core AI infrastructure: vector databases, semantic retrieval, model gateways, and inference pipelines.
• Implement inference optimization and caching to keep latency and cost within target.
• Set up and maintain observability for LLM systems - logging, tracing, evals monitoring, cost tracking.
• Support production incidents and on-call for AI systems, including runbooks and postmortems.
• Work with the Principal AI Full-Stack Engineer to implement architecture decisions and contribute to full-stack features when needed.

Experience & Qualifications

• Solid experience in Python or TypeScript, with working knowledge of backend infrastructure and cloud-native deployment (K8s or serverless).
• Hands-on experience with vector databases, embedding models, and model deployment/serving patterns.
• Some experience with LLM inference optimization, caching, and observability tooling.
• Familiarity with RAG pipelines, function/tool calling, or agent frameworks (LangGraph, LlamaIndex, or similar) - deep expertise not required, willingness to grow into it is.
• Comfortable operating in production environments and taking ownership of reliability and performance.
• High agency and a builder mindset - willing to dig into infra problems without waiting for complete specs.

Nice to Have

• Experience with secure code execution sandboxes (gVisor, Firecracker, WASM) or long-running workflow orchestration.
• Exposure to model routing across providers or agent memory/state architectures.
• Interest in distributed systems, cost governance, or FinOps for AI workloads.
• Finance or insurance domain experience (not required - engineering fundamentals and learning velocity matter more).

Our stack: Python, TypeScript, React/Next.js, Postgres, Kubernetes, and various vector databases and LLM providers. Prior experience with every part isnt required - strong fundamentals and fast learning matter more.