Machine Learning Engineer, Implicit Signals

OpenAI • San Francisco, CA

26d • $381,000 - $510,000

About The Position

Our team builds classification and evaluation systems that give post-training and research teams fast, reliable feedback on model behavior. We combine machine learning and production engineering to make these capabilities accurate, efficient, and useful at scale, helping researchers assess changes and improve models and products. We work closely with research teams to develop useful measurements and make them practical to run. Our work spans classifier development, rigorous evaluation, and efficient production inference, with ownership from initial experimentation through deployment and continued improvement.

We’re looking for a machine learning engineer to develop new classification and evaluation capabilities and bring them into production. You’ll help turn open-ended questions about model behavior into well-defined ML problems, build methods that address them, and establish how reliably those methods work. This role combines traditional machine learning, model evaluation, and real-time engineering. You’ll own classifiers throughout their lifecycle, including supervised fine-tuning, distillation, evaluation, deployment, and production inference. You’ll work closely with researchers to identify valuable problems and with software engineers to make promising approaches useful at scale.

Requirements

• Experience taking ML projects from problem formulation and experimentation through production deployment.
• Strong foundations in supervised learning, statistics, and experimental design.
• Practical experience evaluating models, investigating systematic errors, and working with imperfect labels.
• Strong software engineering skills and the ability to build maintainable production ML systems.
• Experience reasoning about inference performance and the tradeoffs between quality, latency, and compute cost.
• The ability to combine careful scientific judgment with a practical approach to shipping and operating software.
• Comfort working closely with researchers and engineers on open-ended problems.
• Fluency in using AI agents to move quickly across multiple workstreams in a fast-paced environment.

Nice To Haves

• Experience with model distillation, representation learning, calibration, or efficient inference is a plus.

Responsibilities

• Build, deploy, and operate production classification and evaluation systems that provide useful feedback to post-training and research teams.
• Optimize production inference, including model serving, batching, caching, throughput, latency, compute utilization, and cost.
• Train and optimize classifiers using supervised fine-tuning and distillation, validating quality and efficiency before deployment.
• Own the reliability and observability of deployed classifiers, diagnose production issues, and improve their performance over time.
• Design rigorous evaluations that assess accuracy, calibration, generalization, and potential measurement bias while guiding production tradeoffs.
• Partner with software engineers to integrate models into reliable execution systems and support safe rollouts.
• Build reusable engineering tools that make classifier training, evaluation, deployment, and iteration faster and more repeatable.
• Work with post-training researchers and data scientists to translate their needs into modeling objectives, evaluation criteria, and production requirements.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed