AgentOps Engineer
Role details
Job location
Tech stack
Job description
- Design and operate agentic AI solutions end-to-end in production: deployment, monitoring, incident handling, and recovery
- Design and operate secure, scalable cloud infrastructure for agentic AI across AWS/Azure (Terraform, containers etc.)
- Build observability for AI agents, covering traces, tool calls, reasoning steps, latency, cost, quality metrics, and failure modes
- Establish continuous feedback loops using production data, automated evaluation and user signals
- Implement CI/CD for models, agents, prompts, tools, and configurations, with gated promotions and safe rollbacks
- Manage versioning and control rollout of agents including validated model upgrades
- Diagnose and resolve AI-specific production issues such as hallucinations, tool failures, latency and cost anomalies and so on
- Contribute to shared AgentOps standards, runbooks, and ways of working
Requirements
- Relevant background as DevOps, platform or MLOps engineer
- Proficiency in automating with languages like Python and scripting
- Experience with Azure/AWS/GCP, CI/CD, Docker and so on
- Understanding of reliability engineering, incident management, and post-mortems
- Experience with observability tooling (OpenTelemetry, logging, metrics, tracing)
- Understanding of distributed systems and system design
- Experience deploying and managing agents, evacuations, knowledge bases etc.
- Familiarity with frameworks (LangGraph, CrewAI, Strands and similar).
Tech stack example: Python, Strands, AWS AgentCore, AWS Bedrock, MCP, Mlflow, OTel, Docker, GitHub Actions
What you bring You take a role model approach to AI first operations, with a focus on observability and continuous improvement. You have an operational mindset, and care about reliability, failure modes, and recoverability. You communicate and collaborate effectively across roles and teams, and you take true ownership to the team's goals.
Benefits & conditions
You'll work on challenging and meaningful tasks in a strong engineering culture with solid opportunities for professional growth and career development. We offer attractive pension and insurance schemes, as well as employee benefits on DNB's products. You'll also have access to company cabins across Norway, sports, cultural and social activities, and a wide range of employee discounts. We support flexibility in everyday work through flexible working hours, a hybrid way of working, extra days off, and reduced working hours from May to August (summertime).