Square One Resources is seeking a Senior AI DevOps Engineer to join a dynamic project focused on taking AI solutions from concept to production. This role involves building robust infrastructure, implementing observability, and creating workflows that empower engineering teams to deliver high-quality AI-assisted software.
Key responsibilities
- Build and operate production-grade AI agents and AI-enabled tools that support operational teams.
- Design agentic systems using frameworks like LangGraph and LangChain, including RAG and tool calling.
- Lead AI observability efforts using Langfuse and OpenTelemetry to ensure quality, cost-efficiency, and performance.
- Develop an AI SDLC harness to plan, validate, and govern the delivery of AI-assisted software changes.
- Maintain infrastructure, CI/CD pipelines, and GitOps workflows to support scalable AI services.
Requirements
- Over 5 years of experience in DevOps, Platform Engineering, or SRE roles.
- Strong proficiency in Python, with additional experience in Go being a significant advantage.
- Hands-on experience operating production LLM applications and agentic workflows.
- Deep knowledge of AWS, Kubernetes, Helm, and GitOps tools like ArgoCD.
- Proven ability to build internal developer platforms and engineering automation tools.
What we offer
- Opportunity to work on cutting-edge AI infrastructure projects with global reach.
- Collaboration with cross-functional teams to solve complex operational challenges.
- A professional environment backed by over 25 years of recruitment expertise.
- Full remote work flexibility to support your professional growth and work-life balance.