Software Engineer, Data & AI Platform

We are looking for an Engineer with strong data engineering and AI systems experience to build the data, evaluation, and observability foundation for production-grade LLM agents used in complex audit workflows.

This role sits at the intersection of backend engineering, data engineering, AI infrastructure, and LLM operations. You will work hands-on in our backend and agent architecture, building the systems that help us evaluate, monitor, debug, optimize, and continuously improve AI agents in production.

This is not a traditional analytics, BI, or dashboarding role. You should expect to write production code, design infrastructure, work inside backend systems, and directly improve the quality, cost, reliability, and performance of LLM-based agents., You will help building and operating the technical infrastructure around our AI agents, with a focus on data infrastructure, evaluation, observability, and optimization. Your work will include:

• Building online and offline evaluation systems for LLM agents, including pipelines that use golden datasets, ground-truth data, human review workflows, and experiment results.
• Creating automated quality gates so changes to prompts, context, models, or agent logic can be tested before reaching production.
• Analyzing large volumes of agent traces and executions to identify failure modes, quality regressions, latency issues, reliability gaps, and cost optimization opportunities.
• Working with columnar data stores and analytical databases such as BigQuery, ClickHouse, or similar technologies.
• Building reliable data retention and replay mechanisms for long-term analysis of production agent behaviour.
• Creating observability tooling for trace analysis, experiment monitoring, production dashboards, logging, tracing, and debugging.
• Working inside our core backend and agent architecture, including building new agents or improving existing agents when needed.

You will fit into this role if you:

• Have strong Python and/or backend engineering experience.
• Have strong SQL skills and are comfortable working with large datasets.
• Have deployed and operated systems in the cloud, ideally on GCP.
• Have practical experience designing data pipelines, ETL/ELT workflows, event-processing systems, or feedback loops for production data.
• Are comfortable working with analytical databases, data warehouses, columnar stores, and high-volume event or trace data.
• Understand system design, reliability, observability, monitoring, logging, debugging, and operational trade-offs.
• Can work in complex existing systems and quickly build a mental model of how they operate.
• Bring senior-level engineering judgment: you can make architectural decisions, communicate trade-offs, and build systems that other engineers can extend.
• Are comfortable with ambiguity, able to reason from first principles, and excited to build infrastructure for AI systems that are actively used in production.

Nice-to-haves that are a plus:

• Building infrastructure around LLM-based products or agentic systems, including optimizing LLM usage, context windows, reasoning tokens, or model selection.
• Working with production traces from complex distributed systems.
• Building internal platforms for engineers, domain experts, or operations teams.
• Using workflow orchestration systems such as Temporal or similar.
• Familiarity with audit, finance, compliance, or other high-accuracy domains.
• Experience in an early-stage startup or fast-moving engineering environment.

No one checks every box. If you’ve shipped retrieval systems and like owning evaluations and pipelines, let’s talk.

• Attractive compensation: competitive salary plus significant equity
• Personal development: Learning budget for courses and conferences
• Startup perks: Flexible vacation, team lunches, retreats, central Berlin office

We’re Cortea, a Berlin startup transforming audits with AI. Manual, document-heavy audits waste expert time while demand keeps rising. Our AI-powered software and specialized AI agents remove the repetitive work so auditors can focus on judgment.