Senior Site Reliability Engineer

About Deploy

Deploy is an intelligence infrastructure platform that gives developers and enterprises access to open source and proprietary AI models. For leading open source LLMs, Deploy operates an optimized model inference engine that keeps costs and latency low while maintaining high throughput. Deploy also offers a set of proprietary AI models that address challenges in content safety, AI & deepfake detection, sponsorship intelligence, and IP & publicity protection. Trusted by the world's largest and most innovative organizations, Deploy's solutions unlock high-performance AI model inference at production scale.

Deploy has raised more than $200M from leading investors, including Tomales Bay Capital, General Catalyst, 8VC, Glynn Capital, Bain & Company, Visa Ventures, and others. The company has more than 250 employees across offices in San Francisco, Seattle, New York, and Delhi.

DevOps and Systems Team

Our unique machine learning needs led us to open our own data centers, with an emphasis on distributed high performance computing integrating GPUs. Even with these data centers, we maintain a hybrid infrastructure with public clouds when the right fit. As we continue to commercialize our machine learning models, we also need to grow our DevOps and Site Reliability team to maintain the reliability of our enterprise SaaS offering for our customers. Our ideal candidate is someone who is able to thrive in an unstructured environment and takes automation seriously. You believe there is no task that can’t be automated and no server scale too large. You take pride in optimizing performance at scale in every part of the stack and never manually performing the same task twice.

Responsibilities

Automate manual operational processes

Improve workflows of developer, data, and machine learning teams

Manage secure integration and deployment tooling

Create, maintain, monitor, and audit secure infrastructure

Manage a diverse array of technology platforms, following best practices and procedures

Participate in on-call rotation and root cause analysis

Maintain awareness of industry best practices for data maintenance handling as it relates to your role

Adhere to policies, guidelines and procedures pertaining to the protection of information assets

Report actual or suspected security and/or policy violations/breaches to an appropriate authority

Requirements

Minimum 3 - 5 years of previous experience in development, operations, IT, or a related field

Comfortable working on Linux infrastructures (Debian) via the CLIAble to learn quickly in a fast-paced environment

Able to debug, optimize, and automate routine tasks

Able to multitask, prioritize, and manage time efficiently independently

Able to physically lift equipment at least 30 pounds

Can communicate effectively across teams and management levels

Degree in computer science, or similar, is an added plus!

Technology Stack

Operating Systems - Linux/Debian Family/Ubuntu

Configuration Management - Chef

Containerization - Docker

Container Orchestrators - Mesosphere/Kubernetes

Scripting Languages - Python/Ruby/Node/Bash

CI/CD Tools - Jenkins

Network hardware - Arista/Cisco/Fortinet

Hardware - HP/SuperMicro

Storage - Ceph, S3

Database - Scylla, Postgres, Pivotal GreenPlum

Message Brokers: RabbitMQ

Logging/Search - ELK Stack

AWS: VPC/EC2/IAM/S3

Networking: TCP / IP, ICMP, SSH, DNS, HTTP, SSL / TLS, Storage systems, RAID, distributed file systems, NFS / iSCSI / CIFS

Who We Are

We are a group of ambitious individuals who are passionate about creating a revolutionary AI company. At Deploy, you will have a steep learning curve and an opportunity to contribute to one of the fastest growing AI start-ups in San Francisco. The work you do here will have a noticeable and direct impact on the development of the company.

Thank you for your interest in Deploy and we hope to meet you soon!

The current expected base salary for this position ranges from $160,000 - $250,000. Actual compensation may vary depending on a number of factors, including a candidate’s qualifications, skills, competencies and experience, and location. Base pay is one part of the total compensation package that is provided to compensate and recognize employees for their work; stock options may be offered in addition to the range provided here.