обновлено 8 дней назад
Senior Software Engineer (Inference Platform)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior Software Engineer (Inference Platform): Developing and operating high-performance inference platforms for large-scale machine learning models in drug discovery with an accent on scalability, reliability, and cloud infrastructure. Focus on architecting next-generation inference services, optimizing GPU workloads on GCP/Kubernetes, and partnering with research teams to advance rational drug design.
Location: London, United Kingdom. Hybrid working requires coming into the office three days a week, currently Tuesday, Wednesday, and one additional team-dependent day.
Company
develops AI models and computational drug design technologies to accelerate scientific discovery and the development of new medicines.
What you will do
- Develop and operate an inference platform serving machine learning model fleets for scientific applications.
- Define the platform strategy and build roadmaps for its continued maturity.
- Architect and optimize inference services for high throughput, scalability, and feature parity across the model-serving stack.
- Identify and solve core scaling limits as data volumes and model sizes increase.
- Make technical decisions on tooling and architecture while partnering with science, product, and operations teams.
- Deliver reliable, well-tested, user-focused platform features.
Requirements
- Experience architecting and managing large-scale AI/ML workloads in production.
- Significant experience deploying and managing complex workloads with Kubernetes, including GKE.
- Expertise in cloud compute design on Google Cloud Platform.
- Professional familiarity with NVIDIA GPU generations and high-performance computing.
- Strong programming skills and a reliability-first approach to software development.
- Ability to work from London and attend the office three days per week.
Nice to have
- Experience spanning ML software engineering and infrastructure SRE roles.
- Experience leading multidisciplinary projects and managing complex stakeholder requirements.
- Familiarity with workload scheduling, ML efficiency research, and hardware benchmarking.
- Experience with Google TPU generations and specialized ML-driven R&D cycles.
Culture & Benefits
- Collaborative, interdisciplinary environment connecting drug discovery, machine learning, science, product, and operations.
- Values centered on thoughtful work, initiative and integrity, determination, and collaboration.
- Shared learning and support for employees with diverse experiences and perspectives.
- Hybrid work model designed to support in-person knowledge sharing and relationships.
- Accommodations are available for additional needs that affect participation in the hybrid approach.
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 →
Похожие вакансии
9 дней назад
London - ML Ops Engineer II (Experiences) (AI)
10 дней назад
Senior ML Ops Engineer (Experiences)
10 дней назад
Lead Machine Learning Engineer (AI)
9 дней назад
Founding AI Inference Engineer (AI)
12 дней назад
MLOps Engineering Specialist (AWS)
9 дней назад