Principal Engineer, Inference Cloud

Cerebras Systems; Sunnyvale (CA); On-site; USD 230,000 - 340,000; Full time

Job summary

Cerebras Systems is seeking a Principal Engineer for the Inference Cloud Platform in Sunnyvale, CA. You will own the cloud layer behind our Inference Service, ensuring availability, latency, and multi-region scale.

This role requires defining architecture, setting direction across teams, and contributing production code on critical paths. You’ll frame ambiguous problems, trade off options, and drive execution with strong technical judgment.

Qualifications

• 10+ years of software engineering, with IC experience building and operating large-scale distributed systems.
• Deep expertise in distributed systems architecture in cloud environments, including networking, compute orchestration, container platforms, and multi-region production services.
• Strong track record of architectural decisions for highly available, latency-sensitive systems at scale, demonstrated by systems you built.
• Experience optimizing latency, throughput, and efficiency in high-QPS systems; TTFT and tail-latency reduction is a strong plus.
• Strong proficiency in backend or systems languages such as Go, C++, or Python, with ability to contribute production code.
• Experience designing observability and reliability practices, including metrics, logging, tracing, alerting, incident response, and SLI/SLO/SLA-driven operations.
• Ability to influence senior engineers, technical leads, and cross-functional partners through technical credibility, communication, and judgment.
• Experience with ML inference infrastructure, model serving systems, or GPU-accelerated workloads is a plus.

Responsibilities

• Problem Definition & Prioritization. Identify the most important technical problems for the platform, often before there is a clear ask. Make explicit tradeoffs about platform scope with reasoning that holds up to scrutiny.
• Platform Direction. Set long-term technical direction for the Inference Cloud Platform, including multi-region topology and service boundaries.
• Reliability & Performance. Architect active-active systems with rapid failover and graceful degradation; drive latency, throughput, capacity, and resilience improvements.
• Code & Design Reviews. Contribute production code in critical paths and guide architectural decisions including build-vs-buy tradeoffs.
• Production Leadership. Lead on hard production issues, drive observability, incident response, and post-incident improvements.
• Technical Strategy Beyond Your Team. Shape platform-wide decisions on reliability, API design, capacity planning, and deployment strategies.
• Mentorship. Raise the quality of technical decision-making through design feedback and engineering standards.

Skills

Distributed systems

Cloud infrastructure

Go / C++ / Python

Observability & SRE

Multi-region architecture

Production code

Job description

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than GPU-based hyperscale cloud inference services.
This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation.
Cerebras works with the leading model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

About The Role

We'rehiring a Principal Engineer for our Inference Cloud Platform. This team owns the cloud layer behind our Inference Service, including availability, latency, reliability, and multi-region scale.

This is one of the most senior IC roles on the team, for someone who canidentifythe highest-leverage platform problems, set direction across multiple teams, define long-term architecture, and write production code on critical paths.

Many of the key decisions are ambiguous at the outset;you’llneed to frame the problem, make tradeoffs, and drive execution without a clear spec.

The scope includes multi-region traffic architecture, graceful degradation under bursty AI workloads, high-QPS performance, and the operating model for a platform that needs to remain fast and available under changing demand.You'llpartner closely with ML,Productand Infrastructure teams.

Responsibilities

• Problem Definition & Prioritization.Identifythe most important technical problems for the platform, often beforethere'sa clearask. Make explicit tradeoff decisions about what the platform will andwon'tsupport, with reasoning that holds up under scrutiny from senior engineering leadership.

• Platform Direction. Set the long-term technical direction for the Inference Cloud Platform, including multi-region topology, failure domains, service boundaries, and system evolution over time.

• Reliability & Performance.Architect active-active systems with rapid failover and graceful degradation (circuit breaking, backpressure, load shedding) with clear SLOs. Drive improvements in latency, throughput, capacity efficiency, and resilience under unpredictable demand.

• Code & Design Reviews.Contribute production code in critical paths, reviewdesignsand implementations, and make architectural decisions including build-vs-buy tradeoffs with long-term operational consequences.

• Production Leadership. Lead on the hardest production issues and cross-system bottlenecks. Drive observability, incident response, capacity planning, and post-incident improvement with a high standard for operational rigor.

• Technical Strategy Beyond Your Team.Drive platform-wide decisions across adjacent teams on reliability, API design, capacity planning, and deployment strategy through strong technical judgment. Translate product and business requirements into scalable system designs and drive alignment on shared infrastructure decisions.

• Mentorship.Raise the quality of technical decision-making across teams through design feedback, pairing, and clear engineering standards.

Skills & Qualifications

• 10+ years of experience in software engineering, with substantial individual contributor experience building andoperatinglarge-scale distributed systems or cloud infrastructure.

• Deepexpertisein distributed systems architecture in cloud environments, including networking, compute orchestration, container platforms, and multi-region production services.

• Strongtrack recordof making sound architectural decisions forhighly available, latency-sensitive systems at scale,demonstratedthrough systems you built directly.

• Experienceoptimizinglatency, throughput, and efficiency in high-QPS systems. Experience with TTFT and tail-latency reduction is a strong plus.

• Strongproficiencyin backend or systems languages such as Go, C++, or Python, with the expectation that you can contribute production code directly.

• Experience designing observability and reliability practices, including metrics, logging, tracing, alerting, incident response, and SLI/SLO/SLA-driven operations.

• Ability to influence senior engineers, technical leads, and cross-functional partners through technical credibility, communication, and judgment.

• Experience with ML inference infrastructure, model serving systems, or GPU-accelerated workloads is a plus.

Why Join Cerebras

People who are serious about software make their own hardware. At Cerebras, we have built a breakthrough architecture that is unlocking new opportunities for the AI industry. With dozens of model releases and rapid growth, we’ve reached an inflection point in our business. Members of our team tell us there are five main reasons they joined Cerebras:

1. Build a breakthrough AI platform beyond the constraints of the GPU.

2. Publish and open source their cutting-edge AI research.

3. Work on one of the fastest AI supercomputers in the world.

4. Enjoy job stability with startup vitality.

5. Our simple, non-corporate work culture that respects individual beliefs.

Find out more about what it's like to work at Cerebras here!

Cerebras Systems is committed to creating an equal and diverse environment and is proud to be an equal opportunity employer. We celebrate different backgrounds, perspectives, and skills. We believe inclusive teams build better products and companies. We try every day to build a work environment that empowers people to do their best work through continuous learning, growth and support of those around them.