24.10.2026 aktualisiert
100 % verfügbar
Senior Backend Engineer - AI Agent Platforms, Evals & Verification
Frankfurt am Main, Deutschland
Frankfurt am Main +25 km
Skills
Evals & Verification
Expertise in grader and verifier design, LLM-as-judge with cross-family judging, planted-error tests for reviewers, pre-registered agent studies, and Python verifier environments.
Agent Infrastructure
Deep knowledge in tool-call policy guards, test-tamper fences, append-only ledgers, MCP, Claude Code and Codex harnesses, local models, and OpenTelemetry.
Backend Engineering in Go and Python
20 years of production experience building backend systems primarily in Go and Python, including AI systems since 2021, with additional experience in TypeScript, JavaScript, SQL, and Bash.
Kubernetes & Cloud Platform
Hands-on experience with Kubernetes (K3s), Terraform on AWS, GitOps, GitLab CI, Prometheus, Grafana, and Loki for managing production platforms.
AWS DevOps
Running DevOps on AWS using Terraform across ECS, RDS, ElastiCache, IAM, and VPC with full GitOps practices.
Database Technologies
Practical experience with MySQL, MongoDB, and Redis in production backend environments.
PHP Frameworks
Earlier experience with PHP-based frameworks including Symfony and Laravel for backend development.
E-commerce & Payment Systems
Background in building e-commerce promotions with Symfony and AWS, as well as developing multi-currency payment gateways.
Expertise in grader and verifier design, LLM-as-judge with cross-family judging, planted-error tests for reviewers, pre-registered agent studies, and Python verifier environments.
Agent Infrastructure
Deep knowledge in tool-call policy guards, test-tamper fences, append-only ledgers, MCP, Claude Code and Codex harnesses, local models, and OpenTelemetry.
Backend Engineering in Go and Python
20 years of production experience building backend systems primarily in Go and Python, including AI systems since 2021, with additional experience in TypeScript, JavaScript, SQL, and Bash.
Kubernetes & Cloud Platform
Hands-on experience with Kubernetes (K3s), Terraform on AWS, GitOps, GitLab CI, Prometheus, Grafana, and Loki for managing production platforms.
AWS DevOps
Running DevOps on AWS using Terraform across ECS, RDS, ElastiCache, IAM, and VPC with full GitOps practices.
Database Technologies
Practical experience with MySQL, MongoDB, and Redis in production backend environments.
PHP Frameworks
Earlier experience with PHP-based frameworks including Symfony and Laravel for backend development.
E-commerce & Payment Systems
Background in building e-commerce promotions with Symfony and AWS, as well as developing multi-currency payment gateways.
Sprachen
DeutschGrundkenntnisseEnglischverhandlungssicher
Projekthistorie
AI study platform for university courses. Sole engineer who designed, built and ran the whole production platform. Nine services on self-managed Kubernetes in the EU, all model traffic through one gateway, releases in ordered waves, LTI and SSO with a US university.
IT services for national and international clients including SEAT, CUPRA and TU Darmstadt. Running DevOps on AWS (Terraform across ECS, RDS, ElastiCache, IAM, VPC; full GitOps); backend in Go and Laravel on MySQL, MongoDB, Redis.
Own practice in Frankfurt. Consulting and implementation; AI systems since 2021. Projects include feedback-arena (100 impossible tasks at four levels of test feedback), agent fleet for parallel coding work across repositories, agent governance with tool-call policy guards, grader hardening for RL environments, LLM judges and reviewers, and Heimdall quota and metering control plane in Go.