Senior AI Platform Engineer — Production LLMs

Aimlroles; Barcelona; Hybrid; EUR 50,000 - 60,000; Full time

Benefits offered by this job

Competitive, annually reviewed salary

Annual personal development budget

Hybrid working mode

Up to 3 months remote work per year

Private health care

Job summary

Qualifyze is seeking an AI Engineer to join the Engineering team. You will build and deploy production-ready LLM applications, manage cloud infrastructure, and drive end-to-end AI solutions from prototype to production.

The role requires strong Python skills, hands-on experience with LLMs and a pragmatic, ownership-minded approach. You will evaluate models, design CI/CD for AI services, and ensure monitoring, cost controls and reliable deployments across AWS, GCP or Azure.

Qualifications

• 4+ years of experience in software engineering, ML engineering or MLOps/platform engineering, including 2+ years building and deploying LLM-based systems in production.
• Strong Python skills and experience developing production APIs and backend services.
• Practical experience with LLM solutions (e.g. OpenAI, Anthropic, Mistral or similar) and techniques such as RAG, embeddings, vector databases and agent orchestration.
• Experience with cloud platforms such as AWS or GCP and their AI services (Bedrock, SageMaker or Vertex AI).
• Practical experience with Docker, Kubernetes or equivalent technologies, CI/CD and Infrastructure as Code (e.g. Terraform).
• Experience monitoring and operating AI or ML systems in production.
• Ability to communicate technical decisions clearly to engineering teams and business stakeholders.
• A structured and pragmatic approach to problem-solving, with a sense of ownership.
• Experience in regulated industries such as pharma, life sciences, healthcare or fintech is a plus.
• Familiarity with LLM evaluation tools and LLMOps platforms (e.g. Langfuse or MLflow) is a plus.
• Knowledge of AI governance, regulatory frameworks and IT security standards (e.g. EU AI Act, ISO 42001 and ISO 27001) is a plus.
• Experience developing internal tools or supporting developer enablement initiatives is a plus.
• Experience with agentic coding is a plus.

Responsibilities

• Design, develop and deploy production-ready LLM applications, including RAG pipelines, agents and workflow automation.
• Evaluate and select suitable models, frameworks and providers (e.g. OpenAI, Anthropic, Mistral and open-source alternatives) based on the requirements of each use case.
• Develop evaluation processes and benchmarks to measure AI quality, reliability and potential regressions before and after release.
• Design and manage cloud infrastructure for AI workloads using platforms such as AWS, Azure or GCP and Infrastructure as Code.
• Build and maintain CI/CD pipelines for models, prompts and AI services, including automated testing, controlled releases and rollback processes.
• Deploy and scale AI services using containers and orchestration tools such as Docker, Kubernetes or equivalent managed solutions.
• Implement monitoring and observability for AI systems, covering tracing, latency, output quality, drift and potential failure points.
• Establish usage controls and optimise costs through model selection, caching and batching.
• Investigate and resolve production issues across the AI stack.
• Keep up to date with developments in AI and identify techniques and tools that can bring practical value.

Skills

Python

LLM engineering

Backend APIs

Agent orchestration

Stakeholder communication

Tools

Docker

Kubernetes

Terraform

CI/CD

AWS

GCP

Langfuse

MLflow

Bedrock

SageMaker

Vertex AI

Job description

Qualifyze is seeking an AI Engineer to join the Engineering team. You will build and deploy production-ready LLM applications, manage cloud infrastructure, and drive end-to-end AI solutions from prototype to production.

The role requires strong Python skills, hands-on experience with LLMs and a pragmatic, ownership-minded approach. You will evaluate models, design CI/CD for AI services, and ensure monitoring, cost controls and reliable deployments across AWS, GCP or Azure.