Senior Software Engineer (MLOps) – Serving

Key Skills

Aartificial intelligence, DataDog, GPUs, Large Language Models - LLMs, Machine learning techniques, MLOps tools, Python Programming

Job Description

At Datadog, we’re building an AI Platform that powers ML and LLM features across our observability and security products. The Serving team plays a mission-critical role in this platform: ensuring that trained models can be reliably deployed and served at scale in production, across multiple data centers and compute environments.

Our goal is to enable self-serve, performant, and observable model inference workflows. This includes building Ray-based serving infrastructure, deploying inference endpoints on both CPU and GPU, supporting rollback strategies, and enabling shadow traffic, A/B testing, and continuous improvement of deployed models.

We’re looking for a Senior Software Engineer to lead the design and development of our high-scale model serving systems. This role will work across infrastructure, observability, and ML engineering domains to deliver production-ready inference capabilities used by applied scientists and product teams across Datadog.

At Datadog, we place value in our office culture - the relationships that it builds, the creativity it brings to the table, and the collaboration of being together. We operate as a hybrid workplace to ensure our employees can create a work-life harmony that best fits them.

What You’ll Do:

• Architect and build systems for serving ML and LLM models across all data centers with strong SLAs, observability, and reliability.
• Design and optimize Ray-based inference infrastructure to handle both low- and high-throughput workloads.
• Enable applied scientists to deploy and test models via self-service tools, CI/CD pipelines, and rollback mechanisms.
• Implement A/B testing and shadow deployment capabilities to evaluate new model versions in production.
• Collaborate with platform teams to improve GPU provisioning, traffic routing, and runtime performance.
• Instrument inference workflows with rich telemetry (latency, token counts, errors) to drive performance and safety analysis.

Who You Are:

• You have 6+ years of backend or infrastructure engineering experience, including 2+ years working on ML/AI platforms.
• You have experience building distributed systems, ideally in model serving, realtime inference, or large-scale APIs.
• You are proficient in Python, Go, or another systems language and understand performance tuning in high-throughput environments.
• You are familiar with Ray or other inference-serving frameworks (e.g., TorchServe, Triton, BentoML).
• You’ve worked with GPUs and understand how to build infrastructure that supports heterogeneous compute workloads.
• Bonus points: experience with AI observability, rollback strategies, or in-house deployment proxies.

Datadog values people from all walks of life. We understand not everyone will meet all the above qualifications on day one. That's okay. If you’re passionate about technology and want to grow your skills, we encourage you to apply.

Benefits and Growth:

• New hire stock equity (RSUs) and employee stock purchase plan (ESPP)
• Continuous professional development, product training, and career pathing
• Intradepartmental mentor and buddy program for in-house networking
• An inclusive company culture, ability to join our Community Guilds (Datadog employee resource groups)
• Access to Inclusion Talks, our internal panel discussions
• Free, global mental health benefits for employees and dependents age 6+
• Competitive global benefits

Benefits and Growth listed above may vary based on the country of your employment and the nature of your employment with Datadog.