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 all AI services, allowing visibility into how documents and model calls flow through the system, their associated costs, and the root causes of 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 build expertise in observability and platform engineering.

Key Responsibilities
- Instrument services by adding traces, metrics, and structured logs, then transforming this data into actionable dashboards and alerts.
- Assist in running and maintaining the platform, including web and worker services, as well as the underlying queues and datastores.
- Investigate and triage issues by tracing requests end-to-end through the system to identify and resolve problems efficiently.

Required Qualifications
- 1 to 2 years of experience in backend, platform, or full-stack engineering, or equivalent strong internship or 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 a foundational understanding of compute and networking concepts, with eagerness to deepen this knowledge.
- Familiarity with Docker and containerization technologies or a strong desire to learn, along with curiosity about Kubernetes.
- Genuine interest in observability, including comfort with reading and interpreting logs, metrics, and traces to understand request flows and failure points.
- Basic knowledge of large language models (LLMs), including concepts like tokens, context windows, quotas, and the importance of tracing and cost tracking in AI applications.
- Strong debugging skills and comfort working with Git, REST/HTTP protocols, and JSON data formats.
- Experience using AI-assisted development tools (e.g., Claude Code, Cursor) and a demonstrated ability to learn quickly and dive deep into technical challenges.

Preferred Qualifications and Benefits
- Exposure to Kubernetes and Helm or other container orchestration tools.
- Experience with OpenTelemetry, Langfuse, or distributed tracing frameworks.
- 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 including AKS, ACR, Key Vault, and Front Door, or infrastructure as code tools like Terraform or Bicep.
- Understanding of CI/CD pipelines, particularly using GitHub Actions.

This position offers a unique opportunity to grow your skills in cloud-native observability and platform engineering within a cutting-edge AI infrastructure environment. If you are passionate about understanding complex systems and eager to contribute to a mission-critical platform, this role will provide valuable hands-on experience and professional growth.