7 дней назад
Senior Software Engineer, AI / ML Inference Platform (AI)
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior Software Engineer, AI / ML Inference Platform (AI): Building shared AI/ML platform capabilities for GPU training infrastructure, model evaluation, lifecycle tooling, and production inference with an accent on low-latency serving, reproducibility, observability, and operational efficiency. Focus on designing scalable model-serving systems, optimizing GPU workloads, enabling safe releases, and translating ASR and NLP research into dependable enterprise ML systems.
Location: Buenos Aires, Argentina
Company
provides an AI platform for customer experience, combining AI agents and human agents across voice and digital interactions.
What you will do
- Build shared platform capabilities across model training, evaluation, artifact management, release workflows, production inference, and operational feedback.
- Build and operate GPU training infrastructure, improving scheduling, workload isolation, storage, networking, observability, capacity management, and accelerator utilization.
- Develop low-latency, high-throughput, highly available model-serving pathways and integrate training frameworks and inference runtimes.
- Optimize GPU workloads across compute, memory, storage, networking, batching, concurrency, and scheduling.
- Partner with ASR and NLP scientists to translate model capabilities into scalable production systems and advise on reproducibility, evaluation, artifacts, resource requirements, and failure modes.
- Lead technical projects, improve model versioning and release safety, build benchmarking and telemetry tooling, and mentor engineers.
Requirements
- Seven or more years of professional software engineering experience with ownership of backend, infrastructure, distributed, or ML platform systems in production.
- Experience building or operating model-training, model-inference, or ML lifecycle systems.
- Proficiency in Python, Go, or another backend-oriented language.
- Hands-on experience with Linux, containers, Kubernetes, cloud infrastructure, CI/CD, deployment automation, and production operations.
- Experience operating GPU workloads and understanding training workflows, distributed execution, checkpoints, reproducibility, model artifacts, evaluation, and production model behavior.
- Ability to lead ambiguous technical projects, make performance and reliability trade-offs, communicate across disciplines, and mentor engineers.
Nice to have
- Experience with ASR, speech processing, NLP, large language models, or other production model-backed systems.
- Experience with GPU-based or distributed model training and Kubernetes GPU scheduling.
- Experience with vLLM, Triton, TGI, PyTorch, JAX, GKE, experiment tracking, model evaluation, artifact registries, or production model monitoring.
- Experience building internal platforms for scientific and engineering users.
Culture & Benefits
- Work on AI products for business communications and customer experience.
- Build and ship agentic AI products.
- Competitive salary and comprehensive benefits.
- Professional growth opportunities, training programs, and AI tools for employees.
- Inclusive offices designed to support collaboration and connection.
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 →