
About OpenAI
Empowering humanity through safe AI innovation
Key Highlights
- Headquartered in San Francisco, CA with 1,001+ employees
- $68.9 billion raised in funding from top investors
- Launched ChatGPT, gaining 1 million users in 5 days
- 20-week paid parental leave and unlimited PTO policy
OpenAI is a leading AI research and development platform headquartered in the Mission District of San Francisco, CA. With over 1,001 employees, OpenAI has raised $68.9 billion in funding and is known for its groundbreaking products like ChatGPT, which gained over 1 million users within just five day...
🎁 Benefits
OpenAI offers flexible work hours and encourages unlimited paid time off, promoting at least 4 weeks of vacation per year. Employees enjoy comprehensi...
🌟 Culture
OpenAI's culture is centered around its mission to ensure that AGI benefits all of humanity. The company values transparency and ethical consideration...
Skills & Technologies
Overview
OpenAI is hiring a Senior Software Engineer for their Inference team to design and build a load balancer for AI model inference. You'll work with Python and distributed systems to ensure high reliability and performance. This role requires strong experience in debugging complex systems.
Job Description
Who you are
You have 5+ years of experience in software engineering, particularly in designing and building distributed systems. Your expertise includes load balancing and ensuring high availability for critical applications. You are skilled in Python and have a strong understanding of observability tools that help monitor system performance.
You thrive in collaborative environments, working closely with researchers and machine learning engineers to understand the impact of infrastructure on model performance. Your problem-solving skills enable you to debug complex issues effectively, ensuring that systems run smoothly and efficiently.
You are passionate about building reliable systems that can handle high traffic and maintain performance under load. Your experience with traffic routing strategies and long-lived connections makes you an ideal candidate for this role.
Desirable
Experience with AI models and their inference processes is a plus. Familiarity with cloud infrastructure and services can enhance your contributions to the team.
What you'll do
In this role, you will architect and build the gateway and network load balancer that fronts all research jobs at OpenAI. You will ensure that long-lived connections remain consistent and performant, optimizing for both reliability and throughput. Your work will directly impact the performance of AI models used by consumers and enterprises alike.
You will design traffic stickiness and routing strategies that are crucial for maintaining the integrity of model inference. Instrumenting and debugging complex distributed systems will be a key part of your responsibilities, focusing on building world-class observability and debuggability tools.
You will own the end-to-end system lifecycle, from design and code to deployment, operation, and scaling. Collaborating closely with researchers and ML engineers, you will help shape the infrastructure decisions that impact model performance and training dynamics.
What we offer
At OpenAI, you will be part of a mission-driven team that believes in the potential of artificial intelligence to solve global challenges. We offer a competitive salary and benefits package, along with opportunities for professional growth and development. Join us in shaping the future of technology and making a meaningful impact in the world.
Interested in this role?
Apply now or save it for later. Get alerts for similar jobs at OpenAI.
Similar Jobs You Might Like
Based on your interests and this role

Staff Engineer
Cohere is hiring a Staff Software Engineer for their Inference Infrastructure team to build high-performance AI platforms. You'll work with technologies like Python and Docker to deploy optimized NLP models. This role requires experience in machine learning and scalable systems.

Software Engineering
OpenAI is hiring a Software Engineer for their Model Inference team to optimize AI models for high-volume production environments. You'll work with Azure and Python to enhance model performance and efficiency. This position requires 5+ years of experience in software engineering.

Software Engineering
Anthropic is hiring a Senior/Staff Software Engineer for their Inference team to build and maintain critical AI systems. You'll work with distributed systems to serve Claude to millions of users. This position requires significant software engineering experience.

Software Engineering
OpenAI is hiring a Software Engineer for their Inference team to build and optimize infrastructure for multimodal models. You'll work with technologies like Python, TensorFlow, and Kubernetes to serve real-time audio and image workloads. This position requires experience in machine learning and software engineering.

Backend Engineer
Together AI is seeking a Senior Backend Engineer to build and optimize their Inference Platform for advanced generative AI models. You'll work with technologies like Python, Docker, and AWS to enhance performance and scalability. This role requires strong experience in backend engineering and machine learning.