Description

You will design and implement intelligent agents and orchestration frameworks to automate operations, runbooks, and self-healing systems.

This role is hybrid.

Responsibilities

• Build agentic workflows using LangChain/LangGraph to automate operational tasks and ensure system reliability.
• Integrate AI agents with the Dynatrace Intelligence platform, leveraging Grail data lakes and Smartscape for real-time context.
• Architect and optimize advanced RAG pipelines and multi-agent collaboration frameworks.
• Implement AI observability using Dynatrace to track interactions, trace executions, and audit prompts for performance and cost.
• Establish governance safeguards, including approval mechanisms, fallback strategies, and human-in-the-loop controls.

Required Skills

• 8+ years of software engineering experience.
• Strong proficiency in Python.
• Experience with modern orchestration frameworks such as LangGraph or AutoGen.
• Ability to quickly learn the Dynatrace platform, including OneAgent, Davis AI, and the Dynatrace API/SDK.
• Familiarity with CI/CD pipelines and MLOps practices.
• Experience monitoring Kubernetes or microservices environments.
• Strong reasoning skills to balance stochastic GenAI and deterministic decision-making.

Preferred Skills

• Direct experience with Dynatrace Intelligence platform and Smartscape dependency mapping.
• Background in Site Reliability Engineering (SRE) or operational automation.

Key Skills

Education

Any Graduate