Engineering Support

Maite.ai; Madrid; A distancia; EUR 50.000 - 75.000; Jornada completa

Descripción de la vacante

A leading AI company in Spain seeks an AI Platform Engineer to architect the infrastructure powering their legal platform. This role involves building document processing pipelines and working with cloud technologies like Google Cloud and AWS. The company offers a fully remote position with flexible hours, emphasizing a results-oriented culture.

Servicios

Flexible working hours

100% remote work

Formación

• Deep expertise in cloud platforms, particularly Google Cloud or AWS.
• Strong experience with Python and machine learning libraries.
• Proficient in modern JavaScript and TypeScript frameworks.

Responsabilidades

• Architect and maintain the infrastructure for AI legal platform.
• Design and evolve AI infrastructure for multiple LLM providers.
• Build AI document processing pipelines including OCR systems.

Conocimientos

Cloud platforms expertise (Google Cloud, AWS)

Python skills

JavaScript / TypeScript expertise

Kubernetes experience

Infrastructure-as-code (Terraform, CloudFormation)

CI/CD pipeline building for ML systems

Docker experience

Knowledge of vector databases

Monitoring and observability expertise

Background in document processing systems

Familiarity with security and compliance requirements

Start-up experience

Descripción del empleo

AI Platform Engineer @ Maite.ai, we're building AI agents that transform how legal professionals work. We don't just want to make lawyers 10% faster - we want to reimagine legal practice entirely. Our mission is simple but ambitious: fight for a fairer world through technology.

The Opportunity

We're looking for an AI Platform Engineer who will architect and maintain the infrastructure that powers our AI-driven legal platform. This isn't a role where you'll manage existing systems - you'll be building the foundation that takes our AI research from experiments to production-grade tools used by thousands of legal professionals daily.

The Challenge

How do you build infrastructure that's reliable enough for legal work (where accuracy matters), fast enough for real-time document analysis, and flexible enough to integrate the latest AI breakthroughs?

• Design and evolve our AI infrastructure across Google Cloud, AWS, and specialized services (Qdrant, Supabase, Sentry) to support multiple LLM providers (OpenAI, Anthropic, Gemini) and vector search at scale.
• Build and improve AI document processing pipelines, including OCR systems, text extraction from complex legal documents, robust monitoring and observability for AI systems in production—track model performance, latency, costs, and reliability.
• Create CI / CD pipelines that automate model deployment, testing, and rollback strategies.
• Implement best practices for data protection, access control, and compliance (critical in legal tech).
• Design infrastructure for AI agents that can reason, use tools, and complete multi-step legal tasks independently.
• Collaborate closely with engineers, the Q&R (Quality & Research) team, product, and CTO to understand needs and translate research breakthroughs into production features.
• Optimize for cost and performance—ensure we can scale efficiently without burning budget on unnecessary compute.

Qualifications

• Deep expertise in cloud platforms (Google Cloud and / or AWS) including compute, storage, networking, and managed ML services.
• Strong Python skills and experience with the ML ecosystem: scikit-learn, PyTorch / TensorFlow, LangChain, LlamaIndex, or similar frameworks.
• Modern JavaScript / TypeScript expertise with React, Next.js, Node.js, and API design.
• Production Kubernetes experience: deploying, managing, and scaling containerized ML workloads in production environments.
• Infrastructure-as-code experience (Terraform, CloudFormation, Pulumi) for managing cloud resources.
• Proven track record building CI / CD pipelines for ML systems—automating training, testing, deployment, and monitoring.
• Experience with Docker and container orchestration for deploying and scaling ML workloads.
• Knowledge of vector databases (Qdrant, Pinecone, Weaviate) and semantic search architectures.
• Monitoring and observability expertise (Sentry, Datadog, Prometheus, Grafana, or equivalent).
• Background in document processing systems (OCR, PDF parsing, layout analysis).
• Familiarity with security and compliance requirements in regulated industries (legal, healthcare, finance).
• Previous experience in early‑stage startups or small, high‑impact teams.
• Ability to take the right balance between shortcuts and investing in quality.

Remote & Work Flexibility

100% remote – work from anywhere in Spain.

~ Flexible hours – we care about output, not hours logged.