OctoML is a fast-growing startup developing the industry's leading machine learning deployment platform. We enable customers to take ML models to production faster and with greater performance. OctoML's mission is to make AI sustainable and accessible so it can be used to thoughtfully improve lives.We are founded by the creators of Apache TVM, the open-source stack for ML performance and portability. TVM automates the optimization of machine learning models on CPUs, GPUs, edge devices, and specialized accelerators. Building on the success of TVM, our cloud-based OctoML Platform provides choice, automation, and performance to organizations that are taking their trained models to production.Our team consists of experts in machine learning, hardware, cloud services, and compilers. We have secured over $130M in venture capital funding and our team will more than double in size over the next year. We're based largely in Seattle, but have a remote-first culture with people working all over the US and elsewhere in the world.We dream big but execute with focus and believe in creativity, productivity, and a balanced life. We value diversity in all dimensions and are always looking for talented people to join our team! OctoML is growing and looking for Senior Platform Engineer with a focus on SaaS fundamentals to join the team!As a Platform Engineer, you will:

• Build our model optimization-as-a-service product supporting uploading, optimizing, benchmarking, and packaging ML models.
• Scale the platform as we onboard Early Access customers and support more users, models, hardware backends, and other exciting features.
• Work with systems like Kubernetes, Vault, CockroachDB, RabbitMQ, and heterogeneous hardware fleets from cloud VMs to microcontrollers.

Our ideal Platform Engineer will have:

• Experience with a systems programming language such as Rust, Python, Go, C++
• Experience working with SaaS fundamentals such as account management, billing, and business analytics
• Experience developing and deploying systems on cloud infrastructure such as Kubernetes, Consul, and Vault
• Excellent verbal and written communication skills.
• Ability to empathize with co-workers and customers.
• Collaborative working style; able to self manage your time effectively.
• Experience in ML, AI, or optimization is a plus, but not required

BA or BS in Computer Science, Computer Science Engineering, Electrical & Computer Engineering, Electrical Engineering, or a closely-related field is required for this position.Location: Onsite (post-pandemic) in Seattle, WA or RemoteOur Benefits:OctoML aims to provide the resources that employees need to be healthy and comfortable.

• 4 weeks paid personal time off + company paid holidays and company downtime 2x per year
• 100% employer paid premium (for employee and dependents) with a low-deductible plan
• Family & Medical Paid Time Off (includes Maternity, Paternity, Adoption, among others)
• Remote and telework setups for employees (post-COVID)
• Flexible work hours

OctoML is committed to creating a diverse environment and is proud to be an equal opportunity employer. We hire based on an evaluation of abilities and effectiveness. We don't discriminate against employees on the basis of any other personal characteristic or any classification protected by federal, state or local law. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.