AI Infrastructure Engineer (LLM)

TL;DR

AI Infrastructure Engineer (LLM): Building reliable AI infrastructure for manufacturing systems with an accent on MCP servers, model observability, telemetry, and retraining pipelines. Focus on instrumenting production models, designing safe continuous-improvement workflows, and ensuring robust performance, debuggability, and graceful degradation in industrial environments.

Location: Hybrid role based at the headquarters in Maia, Porto District, Portugal.

Company

Develops modular MES software that enables high-performance Industry 4.0 operations across semiconductor, electronics, life sciences, and industrial equipment manufacturing.

What you will do

• Develop and maintain MCP servers connecting language models with manufacturing tools, data sources, and business logic.
• Build telemetry, tracing, dashboards, and alerting infrastructure for model behavior, latency, token usage, cost, and production anomalies.
• Design data collection, evaluation, retraining, feedback, and safe rollout pipelines for continuous model improvement.
• Write production-quality code, tests, documentation, CI/CD workflows, and developer tooling for safe agent-driven changes.
• Participate in code reviews, technical design discussions, troubleshooting, and collaboration with Product, Data, and Platform Engineering.
• Improve reliability through error handling, fallback strategies, graceful degradation, performance tuning, and safety monitoring.

Requirements

• At least one year of hands-on machine learning experience, including model training, testing, overfitting, generalization, bias, and common model families.
• At least one year of hands-on experience with LLMs in production or applied settings, including inference, prompt engineering, evaluation, and tool calling.
• Experience with agentic coding workflows or LLM-based code assistance while maintaining reviews, testing, documentation, and CI discipline.
• Familiarity with server development, APIs, Docker, and Kubernetes.
• Strong software engineering fundamentals, including version control, testing, code review, documentation, and production coding.
• Excellent spoken and written English communication skills; the role requires regular collaboration at the Maia headquarters.

Nice to have

• Manufacturing operations, MES, or Industry 4.0 experience.
• MLOps tools, model monitoring platforms, or ML infrastructure experience.
• Prometheus, Grafana, or similar observability and data pipeline tools.
• Python and AI frameworks such as PyTorch, TensorFlow, or LangChain.

Culture & Benefits

• Work on AI systems with direct impact on real manufacturing operations and factories.
• Collaborate in a focused engineering team building trustworthy AI infrastructure.
• Operate in a rigorous environment that values experimentation, skepticism, technical quality, and continuous improvement.
• Contribute to production systems with strong observability, reliability, security, and engineering standards.