Назад
Company hidden
6 дней назад

Forward Deployed Engineer (AI Inference)

132 000 - 198 000CAD
Формат работы
hybrid
Тип работы
fulltime
Грейд
junior
Английский
b2
Страна
Canada
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Forward Deployed Engineer (AI Inference) (Nutanix AI, Kubernetes, Python/C++/Go): Deploying and optimizing end-to-end AI infrastructure and model-serving systems for enterprise customers with an accent on distributed systems debugging, GPU utilization, and inference performance. Focus on benchmarking modern inference engines, developing deployment automation, and solving complex failures across Linux, Kubernetes, storage, networking, and accelerator architectures.

Location: Vancouver, British Columbia, Canada; hybrid, with a minimum of 3 days per week onsite

Salary: CAD $132,000–$198,000 annually, plus potential sign-on bonus, RSUs, discretionary awards, and benefits.

Company

hirify.global develops the hirify.global Cloud Platform for AI, including GPT-in-a-Box infrastructure for building, fine-tuning, and running generative AI and machine learning models.

What you will do

  • Deploy, configure, and validate hirify.global Enterprise AI workloads across hybrid multi-cloud and on-premises environments for enterprise customers.
  • Diagnose and resolve failures involving GPU orchestration, container networking, storage I/O, model runtimes, Linux internals, hypervisors, and Kubernetes clusters.
  • Develop production-grade automation scripts, CLI tools, Helm charts, and reference architectures for heterogeneous deployment environments.
  • Convert recurring customer issues and performance regressions into reusable frameworks, test beds, product improvements, and code patches.
  • Evaluate and benchmark inference frameworks including vLLM, TensorRT-LLM, TGI, and Triton Inference Server.
  • Optimize model-serving latency, throughput, time-to-first-token, inter-token latency, GPU utilization, and accelerator performance.

Requirements

  • Ph.D. in Computer Science, Computer Engineering, Artificial Intelligence, or a related quantitative field, with academic or thesis focus on AI/ML systems, distributed systems, operating systems, or computer architecture.
  • Strong proficiency in Python and C++ or Go, including systems programming, concurrency, and API development.
  • Deep theoretical and practical knowledge of Linux, systems performance profiling, Docker, and Kubernetes.
  • Hands-on experience deploying, serving, or profiling large language models and diffusion models using PyTorch and open-source serving frameworks such as vLLM, Hugging Face TGI, or Triton.
  • Ability to explain complex distributed-systems failures and create clear technical action plans for customers and internal engineering teams.

Nice to have

  • Internship, research fellowship, or co-op experience in forward deployed engineering, site reliability, infrastructure engineering, or ML platform development.
  • Experience with CUDA, NVIDIA Nsight Systems, Triton kernels, or ROCm.
  • Familiarity with POSIX, S3/Object Store, NVMe-oF, KVM, or AHV.
  • Contributions to open-source inference runtimes, distributed ML libraries, or Kubernetes operators.
  • Experience with speculative decoding, KV cache management, continuous batching, or quantization techniques such as AWQ, FP8, or GPTQ.

Culture & Benefits

  • Hybrid work with at least 3 onsite days per week in Vancouver and remote-work flexibility.
  • Mentorship and guidance from a Technical Manager.
  • RRSP with dollar-for-dollar matching up to 7% of base salary.
  • Mental health coverage, paramedical benefits, paid maternity and parental leave, and bereavement leave.
  • RSUs, an Employee Stock Purchase Plan with a 15% discount, company holidays, sick days, wellness days, and vacation starting at 10 days.
  • hirify.global does not assist with work permits or permanent residence applications, including provincial nomination.

Hiring process

  • The application deadline is 40 days from the posting date, although the posting may be removed earlier if the position is filled or extended.

Будьте осторожны

Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →