About this role
The Search Product Infrastructure team builds the systems that power search experiences across ChatGPT. Engineers on this team partner with model developers, inference infrastructure operators, and index maintainers to bring new model advances and retrieval methods directly into production at scale.
As a senior engineer, the chosen candidate will design, build, and operate distributed systems that connect AI models with search capabilities. Daily responsibilities include handling search orchestration, inference efficiency, experimentation pipelines, and production reliability. The position requires balancing tradeoffs between answer quality, latency, and compute cost while collaborating closely with researchers.
Ideal candidates bring a strong background in large-scale distributed systems and high-throughput online environments. Someone who thrives in ambiguity, enjoys bridging machine learning and systems engineering, and can drive projects from technical design to deployment will find success here.
What you will do
- Design and evolve core services that coordinate search classification, retrieval, ranking, and model inference in production environments.
- Improve end-to-end latency, throughput, and infrastructure efficiency via profiling, caching, request routing, and capacity planning.
- Build experimentation tooling and automation to run reproducible A/B tests, measure product impact, and define success metrics.
- Ensure production reliability through observability, resilient fallback behavior, robust incident response, and operational automation.
- Develop search APIs and tool interfaces that allow models and agents to retrieve information securely while maintaining source attribution.
What you need
- Significant experience designing, building, and operating large-scale distributed systems with a focus on performance, reliability, or resource efficiency.
- Demonstrated background in one or more areas including search, information retrieval, machine learning infrastructure, or inference serving.
- Strong programming and systems debugging skills with the ability to work across diverse languages and unfamiliar production stacks.
- Proven ability to translate ambiguous product requirements into structured technical plans and align cross-functional partners.
- Comfort collaborating with researchers and engineering teams to carry projects from architecture through deployment and measurement.
Benefits
- Offers Equity
- Relocation assistance
Skills and tech stack
Questions candidates ask
Where is the role located and what is the remote work policy?
This role is based in San Francisco, CA. The team uses a hybrid work model requiring 3 days in the office per week.
What is the compensation range for this position?
The salary range is $266K to $445K and includes equity offerings.
What kind of systems and projects will I work on?
You will design, build, and operate systems that connect models with search at ChatGPT scale. Work spans search orchestration, inference efficiency, experimentation, and distributed systems.
Is relocation assistance available?
Yes, relocation assistance is offered to new employees joining this team.