SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
OpenAI's Implicit Signals team builds classification and evaluation systems that provide fast, reliable feedback on model behavior to post-training and research teams. The team combines machine learning and production engineering to deliver accurate, efficient, and scalable capabilities that help researchers assess model changes and improve products.
As a Software Engineer on this team, you will design and build the classification and evaluation platform that enables researchers and data scientists to turn ideas into working measurements and iterate rapidly. You'll develop services, online and offline pipelines, and tools that support this workflow at scale.
Key responsibilities include:
- Design and build software services and APIs for configuring, running, and managing classifiers and evaluations
- Build and operate online and offline classification pipelines supporting reliable, efficient execution at scale
- Improve model-serving performance including throughput, latency, concurrency, and compute utilization
- Create tools that make experimentation, debugging, and iteration straightforward for researchers and data scientists
- Own production reliability, observability, and incident response; reduce operational burden of running the platform
- Partner with machine learning engineers to bring new classification capabilities into production
- Work closely with post-training researchers and data scientists to understand workflows, identify high-impact improvements, and shape the product
This role combines software and data engineering with hands-on production ownership. You'll shape architecture, deliver new capabilities, and keep the system dependable as workloads and requirements evolve.
QUALIFICATIONS & REQUIREMENTS:
- Experience designing, building, and operating software services or distributed systems at scale
- Strong fundamentals in API design, concurrency, caching, performance, and failure recovery
- Ability to investigate complex production problems and make sound architectural tradeoffs
- Track record of owning software from initial design through deployment and ongoing operation
- Strong product judgment and interest in working directly with technical users
- Comfort with ambiguous problems and broad ownership across multiple parts of a system
- Fluency in using AI agents to move quickly across multiple workstreams in a fast-paced environment
- Interest in machine learning, data science, and statistics; experience with model serving, ML platforms, or inference optimization is a plus
