---
title: 'Senior Software Engineer, ML API – AI Inference at Cerebras Systems'
canonical: 'https://feeny.ai/job/senior-software-engineer-ml-api-ai-inference-cerebras-systems-toronto-myd4p8sxeaa5'
type: 'job'
last_seen: '2026-11-03'
---

# Senior Software Engineer, ML API – AI Inference at Cerebras Systems

- **Company:** [Cerebras Systems](https://feeny.ai/companies/cerebras-systems)
- **Location:** Toronto, Canada
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-10-27
- **Last confirmed live:** 2026-11-03
- **Apply:** https://jobs.ashbyhq.com/cerebras/e391dd3c-5908-4533-93f3-fe471187dfa9

## 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](https://openai.com/index/cerebras-partnership/) with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

## About the Role

Cerebras is building a new generation of disaggregated AI inference systems that combine GPU-accelerated prefill with ultra-fast decode on the Cerebras Wafer-Scale Engine.

We are hiring a Senior Software Engineer to build and evolve the ML API layer that makes this heterogeneous serving system accessible, reliable, and easy to use. You will own significant features and components across our inference APIs, model integration layer, and request-routing services, delivering a consistent experience across models and accelerator backends.

This role sits at the intersection of machine learning systems, API design, model serving, and distributed systems. You will translate evolving model capabilities and customer requirements into clear designs, lead implementation across multiple components, and carry features through validation, rollout, and production operation. Your work will help ensure that streaming, sampling, tool use, structured outputs, multimodal inputs, and model configuration behave correctly and consistently.

You will work closely with model enablement, compiler, runtime, cloud infrastructure, product, and customer-facing teams, as well as customers directly. This is a hands-on individual-contributor role with opportunities to lead small project teams, mentor engineers, and improve the quality and reliability of production inference software.

## Responsibilities

- Own features end to end. Design, implement, test, and operate features for chat completions, text generation, streaming, model configuration, tool calling, structured outputs, multimodal inputs, and emerging inference capabilities.
- Lead multi-component delivery. Write clear design documents, evaluate technical tradeoffs, break projects into deliverable milestones, and coordinate implementation with a small group of engineers and partner teams.
- Deliver consistent API behavior. Implement clear request and response semantics across GPU prefill, Cerebras decode, and other inference backends. Maintain compatibility with widely adopted inference interfaces and evolve owned APIs through validation, versioning, and deprecation best practices.
- Enable new models and capabilities. Integrate foundation models, tokenizers, chat templates, generation configuration, sampling methods, and model-specific features into the serving platform.
- Integrate serving components. Extend inference services and their integration with frameworks and runtimes such as vLLM, PyTorch, Hugging Face libraries, LLGuidance, and Cerebras runtime components.
- Support disaggregated inference. Implement routing, state-transfer integration, error handling, retries, cancellation, and request lifecycle management to coordinate GPU prefill with Cerebras decode.
- Deliver measurable performance improvements. Diagnose bottlenecks and improve time to first token, streaming latency, throughput, and resource efficiency through changes to tokenization, serialization, batching, scheduling, and communication.
- Own correctness and release quality. Build conformance tests, model-validation suites, numerical comparisons, integration tests, and performance benchmarks that catch regressions in owned features and support safe releases.
- Strengthen production reliability. Improve service metrics, tracing, logging, alerts, and diagnostic tools. Investigate production incidents, resolve root causes, and follow through on improvements to resilience and incident response.
- Improve customer and developer experience. Partner with product, support, and solutions teams to understand user needs and make practical tradeoffs. Improve configuration, documentation, examples, and debugging workflows.
- Raise the engineering quality bar. Provide thoughtful design and code reviews, mentor less-experienced engineers, share domain knowledge, and proactively remove delivery roadblocks.

## Minimum Qualifications

- 5+ years of software engineering experience, including independent ownership of production services, distributed systems, or substantial software components.
- Strong programming ability in Python and proficiency in Go, C++, Rust, or another language used to build production services.
- Experience designing and delivering features that span multiple components, including documenting designs, evaluating tradeoffs, and coordinating implementation with other engineers.
- Experience building and evolving production APIs, with sound practices for validation, error handling, compatibility, and testing. Familiarity with REST, gRPC, or streaming protocols.
- Experience integrating software across service, framework, runtime, or infrastructure boundaries.
- Experience operating services on Linux using containers, Kubernetes or comparable orchestration systems, and CI/CD.
- Ability to diagnose correctness, reliability, and performance issues across distributed components and deliver measurable improvements.
- Strong communication and collaboration skills, including experience leading technical delivery for a small project and supporting other engineers through reviews or mentorship.
- Ability to turn ambiguous requirements into maintainable software while balancing customer needs, delivery timelines, and operational quality.
- Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related discipline, or equivalent practical experience.

## Preferred Qualifications

- Experience building or operating production ML or LLM inference APIs, including OpenAI-compatible interfaces.
- Experience extending or contributing to vLLM, SGLang, PyTorch, Hugging Face Transformers, Triton, TensorRT-LLM, or another ML systems project.
- Understanding of tokenization, chat templates, generation configuration, logits processing, stopping criteria, tool calling, structured generation, or constrained decoding.
- Experience with disaggregated prefill/decode architectures, KV-cache transfer, prefix caching, chunked prefill, or inference request scheduling.
- Experience building API conformance, model-quality, numerical-comparison, determinism, or performance-regression test systems.
- Experience with multi-model or multi-tenant serving, including routing, admission control, quotas, rate limiting, or capacity-aware scheduling.
- Experience developing performance-sensitive or highly concurrent services in Go, C++, Rust, or a similar language.
- Familiarity with GPU inference, AMD Instinct accelerators, ROCm, CUDA, collective communication, or multi-node model serving.
- Familiarity with reduced-precision inference and quantization formats such as BF16, FP8, FP4, INT8, or INT4.
- Experience building SDKs, developer tools, configuration systems, or self-service ML workflows, or collaborating directly with customers and open-source communities.

## 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:

- Build a breakthrough AI platform beyond the constraints of the GPU.
- Publish and open source their cutting-edge AI research.
- Work on one of the fastest AI supercomputers in the world.
- Enjoy job stability with startup vitality.
- Our simple, non-corporate work culture that respects individual beliefs.

Find out more about what it's like to work at Cerebras [here](https://www.cerebras.ai/join-us)! Apply today and become part of the forefront of groundbreaking advancements in AI! 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. This website or its third-party tools process personal data. For more details, click [here](https://www.cerebras.net/privacy/) to review our CCPA disclosure notice.

## About Cerebras Systems

## Company Overview
- **One-liner**: Cerebras builds wafer-scale AI chips (the largest semiconductors ever made) and supercomputers that deliver up to 15x faster inference than GPUs, offered both on-premises and via cloud APIs.
- **Entity Type**: Public (NASDAQ: CBRS) — filed for IPO and now listed on the Nasdaq.
- **Headquarters**: Sunnyvale, California, United States
- **Founded**: 2015
- **Founders**: Andrew Feldman, Gary Lauterbach, Michael James, Sean Lie, Jean-Philippe Fricker

## Core Business
- **Primary industries**: Semiconductor manufacturing, AI computing hardware and software, cloud AI services.
- **Target customers**: B2B – enterprises, government research labs, cloud service providers, and AI developers.
- **Mission**: “Building impossible technologies so you can too” – accelerating AI through wafer-scale computing.

## Products & Services
- **Wafer-Scale Engine (WSE-3)**: The world’s largest AI chip (215 mm²), 58x larger than a typical GPU, built for ultra‑fast AI training and inference. Manufactured by TSMC.
- **CS-3 Supercomputer**: A single system powered by the WSE-3, delivering record-breaking AI performance for on-premises deployment.
- **Cerebras AI Inference Cloud & Training Cloud**: Pay-as-you‑go APIs that provide drop‑in OpenAI‑compatible access to Cerebras’ hardware for serving, fine‑tuning, and pre‑training models.
- **Condor Galaxy Network**: A series of supercomputers (e.g., CG‑1 with 4 exaFLOPs) built in partnership with G42 for high‑performance AI.

## Market Standing
- **Valuation/Market Cap**: Not disclosed (recently public; market cap data not available in provided sources).
- **Key Metric**: Annual revenue of $78.7 M (latest); total funding of $2.7 B across 15 rounds.
- **Notable Investors/Partners**: G42, OpenAI (signed in 2026), Amazon Web Services (signed in 2026), Meta (Llama API), Perplexity, Mistral, Hugging Face, OpenRouter.
- **Growth Signals**: 
  - 34.3% YoY headcount growth (701 employees).
  - Rapid data center expansion across North America and Europe.
  - Won the HPCwire Readers’ & Editors’ Choice 2025 for Best AI Product/Technology.
  - Named to Forbes America’s Best Startup Employers 2026 and Fast Company Most Innovative Companies 2026 (AI).

## Competitive Advantages
- **Wafer‑scale architecture**: Eliminates interconnect bottlenecks, reducing latency and delivering up to 15x faster inference than GPU clusters.
- **Largest AI chip ever built**: 58x larger than any GPU, enabling massive on‑chip memory (SRAM) and compute density.
- **Full‑stack offering**: Hardware + cloud APIs + on‑prem systems, giving customers deployment flexibility.
- **Strong customer relationships**: Key contracts with OpenAI, AWS, G42, and Mayo Clinic (2024 Gordon Bell Prize work).

## Strategic Focus
- **Scale inference capacity**: Building out data centers to become the world’s #1 provider of high‑speed AI inference.
- **Deepen cloud partnerships**: Expanding pay‑as‑you‑go cloud access and enterprise deployments.
- **Advance wafer‑scale technology**: Continuous R&D on WSE‑3 successors and software stack (compiler, ML workflows).
- **Broaden model support**: Already serving Llama, Gemma, Qwen, Mistral, and more; integrating with Hugging Face and OpenRouter.

## Why Work Here
- **Culture**: “Extraordinary people, breakthrough innovation, global impact” – the company highlights collaborative, low‑overhead teams with little bureaucracy.
- **Work environment**: Hybrid/office with locations in Sunnyvale, San Diego, Toronto, and Bangalore. Inclusive and flexible policy.
- **Perks**: Premium medical/dental/vision, life insurance, generous vacation, 401(k) and Group RRSP retirement plans, daily catered meals, healthy snacks, family‑friendly events (including CEO’s famous BBQ).
- **Engineering focus**: Tackling fundamental challenges in chip design, system software, compiler technology, and ML workflows. Positions range from hardware (Design Verification, Manufacturing) to software (SRE, Compiler, Cloud).
- **Philanthrophy**: Supports local communities and hosts students from around the world for Q&A.

## Sources
1. [cerebras.ai/company](https://www.cerebras.ai/company)
2. [cerebras.ai](https://www.cerebras.ai/)
3. [cerebras.ai/join-us](https://www.cerebras.ai/join-us)
4. [linkedin.com/company/cerebras-systems](https://www.linkedin.com/company/cerebras-systems)

## Other roles at Cerebras Systems

- [Power Manufacturing Test Development Engineer](https://feeny.ai/job/power-manufacturing-test-development-engineer-cerebras-systems-sunnyvale-x2ggztbzgte6) — Sunnyvale, CA
- [Staff Software Engineer, Observability](https://feeny.ai/job/staff-software-engineer-observability-cerebras-systems-sunnyvale-rb9wk9d4aw0y) — Sunnyvale, CA
- [Senior Backend Engineer, Inference Cloud](https://feeny.ai/job/senior-backend-engineer-inference-cloud-cerebras-systems-sunnyvale-3q81ycew9hec) — Sunnyvale, CA
- [Cloud Infrastructure Engineer](https://feeny.ai/job/cloud-infrastructure-engineer-cerebras-systems-sunnyvale-5642y9wwjxaa) — Sunnyvale, CA
- [Staff Software Engineer, GPU Inference](https://feeny.ai/job/staff-software-engineer-gpu-inference-cerebras-systems-toronto-rsjagpay6jdc) — Toronto, Canada
- [Infrastructure Systems Engineer – Linux, Storage & Automation](https://feeny.ai/job/infrastructure-systems-engineer-linux-storage-automation-cerebras-systems-x09zpw8fb6q2) — Sunnyvale, CA
- [AI Inference Core - Senior SDET, Release Integration Testing](https://feeny.ai/job/ai-inference-core-senior-sdet-release-integration-testing-cerebras-systems-k4pm4rc616mx) — Sunnyvale, CA
- [Senior Manager, Service Operations & Enablement](https://feeny.ai/job/senior-manager-service-operations-enablement-cerebras-systems-sunnyvale-qmxx1hpzvnvq) — Sunnyvale, CA
- [SEC Reporting & Technical Accounting Manager](https://feeny.ai/job/sec-reporting-technical-accounting-manager-cerebras-systems-sunnyvale-g6g9t52gcjn6) — Sunnyvale, CA
- [Senior Manager, Production & Fleet Operations](https://feeny.ai/job/senior-manager-production-fleet-operations-cerebras-systems-sunnyvale-tnzs6bz9xfma) — Sunnyvale, CA