Principal Software Engineer, Agent Harness Bridge

OpenAI; San Francisco (CA); On-site; USD 190,000 - 260,000; Full time

Job summary

OpenAI is seeking a Principal Software Engineer to lead the architecture of the Agent Harness Bridge, connecting research and training infrastructure with scalable, reliable backend systems. You will own APIs, interfaces, and workflows used by researchers and internal developers, ensuring safety and efficiency in training environments.

The role calls for strong backend or infrastructure engineering experience, a proven ability to drive cross‑team initiatives, and a product‑minded approach to

Qualifications

• Significant experience building and scaling backend or infrastructure systems in fast‑moving environments.
• Deep strength in API design, systems design, and engineering fundamentals.
• High attention to detail and a deep commitment to correctness, reliability, and operational quality.
• Ability to work directly with demanding technical users while maintaining strong engineering discipline.
• Track record of leading cross‑functional technical efforts and creating clarity across organizational boundaries.
• Strong product sense and user empathy for internal platforms and developer tooling.
• Motivation to enable researchers and accelerate their work, rather than doing research yourself.
• Proficiency in Python; experience with backend platform engineering; Rust experience is a plus.

Responsibilities

• Design, build, and evolve the bridge between the Codex harness and research training infrastructure
• Own major integration surfaces end‑to‑end, from architecture and API design through rollout, operations, and long‑term maintenance
• Build reliable, containerized execution systems that can support demanding training workloads at scale
• Partner closely with research, agent, infrastructure, and platform teams to support new training use cases and harness capabilities
• Design clean, stable interfaces and workflows for highly technical internal users who move quickly and expect strong ergonomics
• Prevent one‑off workarounds from becoming long‑term technical debt by establishing durable abstractions and clear ownership
• Raise the bar for correctness, reliability, operational rigor, and engineering judgment across a critical research‑facing system

Skills

Backend architecture

API design

Systems design

Python

Engineering discipline

Cross-functional leadership

Reliability

Developer tooling

Leadership

Tools

Rust

Python

Job description

About the Team

OpenAI’s research training infrastructure powers how our frontier models are trained and evaluated. The Agent Harness Bridge team sits at the boundary between the Codex harness, research infrastructure, and internal agent systems, ensuring the same agentic coding runtime used in product can also support large‑scale training workloads. This team owns the integration layer that connects harness capabilities into the training stack. The work is highly cross‑functional and high leverage: researchers depend on it to run reliably, platform teams depend on it to evolve cleanly, and failures in this surface can materially affect training velocity and correctness.

About the Role

We’re looking for a Principal Software Engineer to lead the architecture and evolution of the Agent Harness Bridge. You’ll own a critical interface between research and engineering, building the systems, APIs, and operational patterns that let researchers use agentic coding infrastructure safely and effectively in training environments. This role is ideal for a senior backend or infrastructure engineer with strong technical judgment, product sense for highly technical users, and the ability to drive execution across multiple teams.

Responsibilities

• Design, build, and evolve the bridge between the Codex harness and research training infrastructure
• Own major integration surfaces end‑to‑end, from architecture and API design through rollout, operations, and long‑term maintenance
• Build reliable, containerized execution systems that can support demanding training workloads at scale
• Partner closely with research, agent, infrastructure, and platform teams to support new training use cases and harness capabilities
• Design clean, stable interfaces and workflows for highly technical internal users who move quickly and expect strong ergonomics
• Prevent one‑off workarounds from becoming long‑term technical debt by establishing durable abstractions and clear ownership
• Raise the bar for correctness, reliability, operational rigor, and engineering judgment across a critical research‑facing system

Qualifications

• Significant experience building and scaling backend or infrastructure systems in fast‑moving environments
• Deep strength in API design, systems design, and engineering fundamentals
• High attention to detail and a deep commitment to correctness, reliability, and operational quality
• Ability to work directly with demanding technical users while maintaining strong engineering discipline
• Track record of leading cross‑functional technical efforts and creating clarity across organizational boundaries
• Strong product sense and user empathy for internal platforms and developer tooling
• Motivation to enable researchers and accelerate their work, rather than doing research yourself
• Proficiency in Python; experience with backend platform engineering; Rust experience is a plus

Location

This role is ideally based in SanFrancisco due to the close collaboration required with researchers and infrastructure partners.

EEO Statement

We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.