Agentic AI Engineer

QTechBoston, MA
Onsite

About The Position

We are seeking an Agentic AI Engineer to design and implement intelligent agents and orchestrations using frameworks like LangChain/LangGraph. This role involves automating operations, runbooks, and self-healing systems. A key aspect of this position is integrating AI agents with the Dynatrace Intelligence platform, utilizing Grail data lakes and Smartscape dependency mapping for real-time context. You will also architect and optimize advanced RAG pipelines and multi-agent collaboration frameworks. Additionally, you will use the Dynatrace AI Observability app to track interactions, trace executions, and audit prompts for performance and cost. Establishing approval mechanisms, fallback strategies, and human-in-the-loop controls for secure and compliant autonomous operations is crucial. This role requires close collaboration with SREs, developers, and OPS teams to transform operational challenges into deployed AI solutions.

Requirements

  • Experience with frameworks like LangChain/LangGraph.
  • Experience integrating with the Dynatrace Intelligence platform.
  • Familiarity with Grail data lakes and Smartscape dependency mapping.
  • Experience architecting and optimizing RAG pipelines.
  • Experience with multi-agent collaboration frameworks.
  • Experience using AI Observability tools for tracking, tracing, and auditing.
  • Knowledge of governance, approval mechanisms, fallback strategies, and human-in-the-loop controls.
  • Ability to collaborate with SREs, developers, and OPS teams.

Responsibilities

  • Design and implement intelligent agents and orchestrations using frameworks like LangChain/LangGraph to automate operations, runbooks, and self-healing systems.
  • Integrate AI agents with the Dynatrace Intelligence platform, leveraging Grail data lakes and Smartscape dependency mapping for real-time context.
  • Architect and optimize advanced RAG pipelines and multi-agent collaboration frameworks.
  • Use the Dynatrace AI Observability app to track interactions, trace executions, and audit prompts for performance and cost.
  • Establish approval mechanisms, fallback strategies, and human-in-the-loop controls to ensure secure and compliant autonomous operations.
  • Work closely with SREs, developers, and OPS teams to turn operational pain points into deployed AI solutions.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service