Senior AI Engineer - APM Integrations

Datadog, Inc.

Job Overview

Location

Germany, Remote; Italy, Remote; Spain, Remote

Job Type

Full-time

Full Job Description

📋 Description

• As a Senior AI Engineer on the APM Integrations team at Datadog, you will be at the forefront of innovation, developing cutting-edge AI-assisted tools designed to revolutionize how engineers build and maintain integrations. This role offers a unique opportunity to shape the future of engineering workflows by creating intelligent systems that enhance productivity, ensure quality, and foster trust in production environments.
• Your primary focus will be on building sophisticated agent workflows. These workflows will guide an integration need from its initial planning stages through to implementation and validation, incorporating human oversight at critical checkpoints to ensure accuracy and alignment with project goals. This end-to-end approach guarantees that the AI-driven solutions are not only efficient but also robust and reliable.
• You will architect and develop systems capable of synthesizing vast amounts of contextual information. This includes drawing insights from codebases, technical documentation, product specifications, real-time telemetry data, and historical incident reports. The goal is to generate code changes and integration updates that meticulously adhere to Datadog's established conventions and consistently meet customer expectations, ensuring seamless integration and optimal performance.
• A significant part of your role will involve generating and evolving integration code and associated tests. This includes crafting comprehensive end-to-end scenarios that accurately mirror real-world customer workloads and core product features. By simulating realistic usage patterns, you will ensure that the integrations are thoroughly tested and performant under diverse conditions.
• You will be instrumental in designing and implementing advanced evaluation harnesses. These systems are crucial for preventing silent regressions and maintaining the integrity of AI-generated outputs. This includes developing and utilizing golden sets, scenario baselines, semantic checks, performance thresholds, and robust release gating mechanisms to guarantee consistent quality and reliability over time.
• Furthermore, you will build portfolio-level automation capabilities. This involves creating systems that can proactively manage updates for upstream breaking changes, facilitate the rollout of new tracer features across the entire integration catalog, orchestrate migrations to new schemas or semantics, and strategically expand test coverage. This broad scope of automation will significantly enhance the efficiency and maintainability of Datadog's integration ecosystem.
• Collaboration is key in this role. You will partner closely with Product Managers, Support Engineers, and the various integration-owning teams. Your objective will be to ensure that the AI-driven solutions are not only technically sound but also highly adoptable, trustworthy, and seamlessly embedded into the daily workflows of our engineering teams. This cross-functional collaboration ensures that the tools we build directly address the needs of our users and contribute to a more efficient and effective engineering culture.
• You will define what constitutes 'good' performance and quality for these AI tools, establishing clear metrics to measure their impact and guide iterative improvements. This data-driven approach ensures that our AI solutions continuously evolve and remain at the cutting edge of technological advancement.
• This is a senior position with a high degree of ownership, encompassing the entire lifecycle of AI-powered tools, from initial prototyping and development to production deployment and ongoing maintenance and support. You will have the autonomy to drive significant projects and make a tangible impact on Datadog's product and engineering practices.
• You will contribute to Datadog's hybrid work environment, balancing focused individual work with collaborative team interactions. While remote, you will be an integral part of a dynamic team, contributing to a culture of innovation and continuous improvement.

🎯 Requirements

• 6+ years building backend systems in languages such as Go, Java, or .NET, with a strong emphasis on simplicity, correctness, and performance.
• Proven experience delivering LLM/agent features into production environments, including expertise in prompting, tooling, evaluation, and implementing safety/guardrails.
• Demonstrated ability to navigate ambiguity, iterate from prototype to production, and measure impact using clear, data-driven metrics.

🏖️ Benefits

• New hire stock equity (RSUs) and employee stock purchase plan (ESPP).
• Continuous professional development, product training, and clear career pathing opportunities.
• Intradepartmental mentor and buddy program for in-house networking and support.
• Access to Community Guilds (Datadog employee resource groups) and Inclusion Talks for professional and personal growth.

Skills & Technologies

Java

Datadog

Data Science

Senior

Remote

Ready to Apply?

Apply Externally

You will be redirected to an external site to apply.

Datadog, Inc.

Visit Website

About Datadog, Inc.

Datadog, Inc. provides a cloud-scale monitoring and analytics platform that unifies infrastructure metrics, application performance traces, and log data. It offers real-time dashboards, machine-learning alerts, distributed tracing, synthetic monitoring, and security analytics for cloud, on-premises, and hybrid environments. The company serves technology, financial services, retail, and government organizations worldwide, helping them reduce downtime, optimize resource usage, and improve software performance across dynamic, containerized architectures.

View Company Profile