DevOps Engineer

About the Role

Join Dv01 through Haystack and own the MLOps platform and infrastructure side of an innovative AI solution built to prevent financial crises. This role is ideal for a DevOps Engineer who will design, build, and operate cloud-native AI infrastructure and platform tooling in a remote-first environment.

Key Responsibilities

• Design and build cloud-native AI infrastructure and platform tooling.
• Own DevOps and infrastructure for MLOps and agentic systems, including CI/CD and scalable inference.
• Maintain infrastructure for LLM-backed APIs, MCP servers, and agentic systems.
• Integrate MLOps practices: AI-driven monitoring, alerting, and incident response.
• Establish governance, security, and operational guardrails in collaboration with security teams.

What You'll Need

• 8+ years in cloud infrastructure, DevOps, or platform engineering.
• 5+ years in MLOps with production ML/GenAIOps experience.
• Expertise in cloud-native technologies, Kubernetes, containerized workloads, and Infrastructure-as-Code (Terraform).
• Hands-on experience with platforms hosting deep neural networks and LLM runtimes (vLLM, llama.cpp) and PyTorch systems.
• Strong understanding of infrastructure security, IAM, secrets management, and operational risk for AI systems.

What's On Offer

• Unlimited PTO to unplug and rejuvenate.
• $1,000 Learning & Development Fund for professional growth.
• Remote-first environment with flexibility and support.
• Comprehensive medical, dental, vision insurance, plus a 401(k).

Key skills/competency

• DevOps
• MLOps
• AI Infrastructure
• Cloud-native
• Kubernetes
• Terraform
• CI/CD
• Observability
• LLM
• Security