Senior Data / AI Infrastructure Engineer (LLM Systems)

HRvizer is currently supporting a fast-growing AI startup in Berlin in hiring a Senior Engineer to join their core technical team.

The company operates in the AI automation space, building production-grade LLM-based systems that help reduce manual, document-heavy workflows in complex, knowledge-intensive environments.

They are well-funded, already live with paying customers, and currently scaling their engineering organization.

The Role

We are looking for a Senior Engineer with strong backend and data infrastructure experience to build the foundation for evaluation, observability, and performance optimization of LLM-powered systems.

This role sits at the intersection of:

• Backend engineering
• Data engineering
• AI/LLM infrastructure
• Observability & reliability systems

You will work directly on production systems that monitor, evaluate, and improve AI agents at scale.

This is a hands-on engineering role (not BI / analytics), with direct impact on system performance, cost, and reliability.

What you will do

• Build evaluation frameworks for LLM agents (offline + online testing, datasets, human feedback loops)
• Design automated quality gates for changes in models, prompts, and agent logic
• Analyse large-scale production traces to identify failures, regressions, latency, and cost issues
• Work with analytical databases (BigQuery, ClickHouse or similar)
• Build data replay, retention, and debugging systems for production behaviour
• Develop observability tooling (logging, tracing, dashboards, monitoring)
• Contribute to backend and agent infrastructure where needed

Requirements

• Strong experience in Python and/or backend engineering
• Advanced SQL skills and experience with large datasets
• Experience working in cloud environments (GCP preferred)
• Experience building data pipelines, ETL/ELT, or event-driven systems
• Strong understanding of system design, reliability, and observability
• Ability to work in complex systems and ambiguous environments
• Strong engineering judgment and architectural thinking

Nice to have

• Experience with LLMs, agentic systems, or AI infrastructure
• Experience working with distributed system traces
• Experience building internal platforms or developer tools
• Familiarity with workflow orchestration tools (e.g. Temporal)
• Background in audit, finance, or compliance environments
• Experience in early-stage startups or scale-ups

What’s offered

• High-impact role in a fast-scaling AI company
• Strong ownership from day one
• Competitive salary + equity
• Learning & development budget
• Flexible work culture + team events