What You'll Do
Your responsibilities include but are not limited to:
- Build and operate backend services in Node.js/TypeScript (with Python exposure), designing for reliability, scalability, and real-time performance
- Design, evaluate, and ship LLM-based features end-to-end: prompt engineering, tool calling, structured outputs, guardrails, and fallback strategies
- Own AI feature quality: build evaluation datasets and scorers (e.g., in Braintrust), track regressions, and make evidence-based ship decisions before each release
- Deploy and operate cloud-native services on Kubernetes across major cloud providers (AWS/Azure/GCP), and evolve CI/CD pipelines with GitHub Actions
- Design data models and drive database migrations and performance tuning for real-time workloads (PostgreSQL: connection pooling, indexing, query optimisation)
- Maintain a high testing bar (unit, integration, e2e), debug distributed systems in production with strong observability, and contribute to pragmatic, secure architecture decisions
Who You Are
Before you read on: if you don't have the exact profile described below, but you feel this job description matches your skill set, we still encourage you to apply.
You'll Be a Great Fit If You
- Have 5+ years of backend engineering experience building scalable, resilient systems in Node.js/TypeScript (with some Python)
- Have hands-on production experience building LLM-based features: prompting, tool calling, structured outputs, eval frameworks, and handling real-world failure modes
- Have proven experience deploying and operating services on Kubernetes within at least one major cloud provider (AWS, Azure, or GCP), with solid CI/CD practices
- Have a strong testing culture (unit/integration/e2e), sharp debugging skills for microservices and distributed systems, and a focus on code quality
- Are fluent in English, with a collaborative mindset and the drive to own problems end-to-end — from design to production