Senior Engineer (mfx) for OpenIngest Generative AI

Most AI developer tools operate without any knowledge of how software actually behaves in production. Dynatrace is in a unique position to change that.

Were looking for an engineer who lives at the intersection of open standards distributed systems and AI infrastructure. You will own the path that telemetry from AI workloads takes into Dynatrace from the moment an SDK emits a span in a customers LLM application through ingest validation and into the data model that powers our AI observability product.

This role sits inside Dynatraces Engineering organization and works closely with product design and the platform teams that power Dynatraces AI-observability stack.

Your responsibilities:

• Own OpenTelemetry ingest for AI workloads. Build and maintain the ingest path for OpenTelemetry traces metrics and logs emitted by GenAI applications agents and frameworks. Ensure it is robust performant and faithful to the spec.
• Test and support integrations across the AI SDLC. Validate that popular AI SDKs frameworks and agent runtimes produce telemetry that flows cleanly into Dynatrace. Close the gaps you find in our ingest in upstream instrumentation or in the spec itself.
• Partner with the OneAgent team to align auto-instrumentation context propagation and runtime data collection for AI workloads so customers get a coherent experience whether they instrument manually or rely on OneAgent.
• Push GenAI semantic conventions forward across the industry by representing Dynatrace in the OpenTelemetry GenAI SIG. Propose review and drive consensus on semantic conventions for LLM calls agents tool use evaluations and emerging patterns. Help define what good AI telemetry looks like and make sure the standard reflects real production needs.
• Prototype quickly run user feedback cycles and ship to production
• Collaborate with product and design to identify which developer problems are most worth solving.
• Define technical strategy for the teams AI systems set architectural direction and mentor other engineers.

• 5 years (Senior) of professional software engineering experience
• Demonstrated experience shipping production systems that use LLMs including prompting tool calling evaluation and iteration
• Strong foundation in at least one of: developer tooling (IDEs compilers static analysis code intelligence) AI/ML engineering or large-scale distributed systems
• Hands-on experience with agentic patterns: planning tool use retrieval memory management
• Hands-on experience with LLMs: prompt engineering evaluation frameworks (e.g. LLM-as-a-judge golden datasets pairwise comparisons) or agent frameworks.
• Ability to evaluate and critique AI-generated output. You understand when a model is wrong not just that it is.
• Clear communication with cross-functional partners across product and engineering

• Dynatrace is a leader in unified observability and security.
• We provide a culture of excellence with competitive compensation packages designed to recognize and reward performance.
• Our employees work with the largest cloud providers including AWS Microsoft and Google Cloud and other leading partners worldwide to create strategic alliances.
• Youll get to work at the forefront of innovation with Dynatrace Intelligencethe industrys first agentic operations system. Bringing together deterministic and agentic AI it helps teams understand whats happening why it matters and what to do next automatically.
• Over 50% of the Fortune 100 companies are current customers of Dynatrace.

• We offer attractive compensation packages and stock purchase options with numerous benefits and advantages.
• Due to legal reasons we are obliged to list a salary range for this position which is 61000 up to 92000 gross per year based on full-time employment (38.5 h/week). Weve listed the salary range for transparency but if your experience and skills bring unique value wed still love to hear from youplease apply even if youre outside the range.