Site Reliability Engineer (SRE)

Our mission is to provide developers with a suite of intuitive tools and platforms that simplify the process of integrating LLMs into their software projects. We are building an open-source toolkit that empowers developers to effortlessly build cutting-edge, AI-powered applications. We're at the forefront of generative AI innovation, creating tools that streamline LLM integration, management, and deployment for developers around the world. The Opportunity:

As our SRE, you'll be the guardian of our cutting-edge, LLM-powered developer platforms. You'll work to ensure maximum availability and efficiency, directly impacting the experiences of developers worldwide. What You'll Do:

• Architect for Resilience: Design and implement highly available, scalable systems optimized for LLM workloads.
• Champion Observability: Build robust monitoring, logging, and alerting systems to gain deep insights into system health and potential issues.
• Automate Everything: Drive efficiency through infrastructure-as-code (IaC) and robust CI/CD pipelines.
• Mitigate Risk: Proactively implement disaster recovery, security best practices, and capacity planning strategies.
• Collaborate for Innovation: Work closely with developers to understand platform needs and support the integration of new LLM technologies.

Why Join Embedded LLM

• LLM Frontier: Be at the forefront of a technological revolution, shaping how LLMs transform software development.
• Open-Source Impact: Contribute to a vibrant open-source community with global reach.
• High-Growth Environment: Experience rapid growth and the challenges of scaling cutting-edge AI infrastructure.
• Collaborative Team: Work alongside passionate engineers and pioneers in the LLM space.

Job Requirements

What We're Looking For

• SRE Mindset: 3+ years of experience in Site Reliability Engineering, DevOps, or similar roles.
• Cloud Native: Deep understanding of cloud architecture (ideally AWS, Azure, or GCP) and containerization technologies (Docker, Kubernetes).
• Automation Ace: Strong scripting skills (Python, Ansible, Bash) and expertise in IaC tools (Terraform, CloudFormation, etc.).
• Data-Driven: Proficiency in monitoring and observability tools (Prometheus, Grafana, etc.).
• LLM Curious: Interest in LLMs and their unique infrastructure requirements is a plus.

Nice to Haves:

• LLMOps Understanding: Familiarity with the operational challenges of deploying and managing large language models.
• GPU Expertise: Experience working with GPU-accelerated infrastructure for AI workloads.

Skills

DevOps

Site Reliability Engineering

Cloud Computing

Docker (Software)

Ansible

Bash (Scripting Language)

Cloud-Native Computing

Company Benefits

Benefit from a supportive and team-focused culture that encourages collaboration and values each member's contributions.

We prioritize your professional development, offering opportunities for learning and advancement to help you achieve your career goals.

Additional Info

Experience Level

2 - 20 Years of Experience

Entry Level

Job Specialisation

Computer Engineering, Hardware / Network / Infrastructure (On-Premises / Cloud), System & IT Helpdesk / Database Administrator