Эта вакансия в архиве
Посмотреть похожие вакансии ↓3 месяца назад
Principal Software Engineer (ML Infrastructure)
Описание вакансии
Текст:
TL;DR
Principal Software Engineer (ML Infrastructure): Designing and scaling ML inference platform services with an accent on high-throughput RPC services and distributed systems. Focus on overseeing technical strategy, optimizing GPU utilization for LLM inference, and ensuring system reliability at scale.
Location: Must be based in the US (Bellevue, Los Angeles, New York, Palo Alto, or Seattle). Expected to work in an office 4+ days per week.
Company
Technology company operating , Specs Inc., and Bitmoji, focusing on visual communication and human-centric computing.
What you will do
- Oversee technical strategy and architecture for ML Inference Platform services.
- Design, implement, and scale critical engineering components to support ML inference and deployment.
- Collaborate across teams to translate product requirements into scalable technical solutions.
- Advocate for and apply best practices in availability, scalability, operational excellence, and cost management.
- Provide technical direction that influences the engineering approach across the entire company.
Requirements
- 10+ years of post-Bachelor’s software development experience (or equivalent with Master's/PhD).
- 2+ years of experience in technical leadership or acting as a domain expert for a technical organization.
- Proven experience architecting and developing large-scale distributed systems and high-throughput RPC services.
- Excellent programming and software design skills, including debugging and performance analysis.
- Must be located in one of the specified US office locations and adhere to the 4+ days per week in-office policy.
Nice to have
- Experience with Tensorflow, PyTorch, Kubernetes, GPU, and LLM inference.
- Advanced degree in Computer Science or a related technical field.
- Experience with cross-platform development.
- Ability to drive a portfolio of concurrent engineering projects from research to launch.
Culture & Benefits
- "Default Together" culture emphasizing the value of in-person collaboration.
- Comprehensive medical coverage and emotional/mental health support programs.
- Paid parental leave.
- Compensation packages that allow employees to share in the company's long-term success.