AI Platform Engineer Observability

You will contribute to the development and operation of a self-hosted large language model (LLM) observability platform built on Langfuse. This platform collects traces from various AI services to monitor document and model call flows, analyze costs, and diagnose failures. The codebase is primarily TypeScript/Node.js and runs on Kubernetes (AKS). This role is ideal for early-career engineers who are curious about system behavior in production environments and eager to work on both platform infrastructure and instrumentation.

Key Responsibilities
- Instrument services by adding traces, metrics, and structured logs, and transform this data into actionable dashboards and alerts.
- Assist in running and maintaining the platform, which includes web and worker services, as well as the underlying queues and datastores.
- Diagnose and triage issues by tracing requests end-to-end through the system to identify root causes.

Required Qualifications
- 1 to 2 years of experience in backend, platform, or full-stack engineering, or equivalent strong internship/project experience.
- Proficiency in TypeScript/JavaScript (Node.js) or solid programming fundamentals in another language with a strong willingness to quickly learn TypeScript.
- Practical experience with at least one major cloud provider (Azure, AWS, or GCP) and foundational knowledge of compute and networking concepts, with eagerness to deepen expertise.
- Familiarity with Docker and container technologies, or a strong desire to learn, along with curiosity about Kubernetes.
- Genuine interest in observability, including understanding request flows, failure modes, and comfort with analyzing logs, metrics, and traces.
- Basic understanding of large language models, including concepts such as tokens, context windows, and quotas, and awareness of the importance of tracing and cost tracking for AI applications.
- Strong debugging skills and comfort using Git, REST/HTTP protocols, and JSON data formats.
- Experience with AI-assisted development tools (e.g., Claude Code, Cursor) and a fast learner who enjoys deep technical exploration.

Preferred Qualifications and Additional Skills
- Exposure to Kubernetes/Helm or other container orchestration tools.
- Experience with OpenTelemetry, Langfuse, or distributed tracing systems.
- Familiarity with frontend frameworks and tools such as Next.js, React, tRPC, Prisma, or BullMQ.
- Knowledge of databases like PostgreSQL, ClickHouse, or Redis.
- Specific experience with Azure services such as AKS, ACR, Key Vault, Front Door, or infrastructure-as-code tools like Terraform or Bicep.
- Experience with CI/CD pipelines, particularly using GitHub Actions.

This position offers an excellent opportunity to grow your skills in cloud-native observability and AI infrastructure, working within a cutting-edge environment focused on understanding and optimizing complex AI workflows.