AI Platform SRE: Reliability, Observability & Scale

Schonfeld; New York (NY); On-site; USD 175,000 - 225,000; Full time

Job summary

You’ll define reliability standards, own incident management, and drive improvements for agents, proxies, and RAG pipelines. Strong Python, AWS, Kubernetes, and CI/CD experience are required.

Qualifications

• 5+ years of professional cloud automation or site reliability engineering experience.
• Experience with Python
• Experience building REST APIs and event-driven architectures.
• Experience with relational and NoSQL databases (Postgres, MySQL, DynamoDB, ElasticSearch).
• Experience with AWS, Kubernetes, GitHub Actions, and modern CI/CD pipelines.

Responsibilities

• Set reliability standards: SLOs, error budgets, incident runbooks.
• Own observability, incident response, reliability, and scalability of our AI platform.
• Ensure high availability, accuracy and efficiency of agents, gateways, LLM proxies, and RAG pipelines.
• Assist users via help channel: investigate root causes, provide solutions, monitor dependencies, communicate updates.
• Improve core platform and developer workflows; enforce best practices across teams.

Skills

Python

REST APIs

Async architectures

AWS

Kubernetes

CI/CD

Observability

DataDog

Problem solving

Tools

DataDog

Postgres

MySQL

Job description

You’ll define reliability standards, own incident management, and drive improvements for agents, proxies, and RAG pipelines. Strong Python, AWS, Kubernetes, and CI/CD experience are required.