Senior Software Engineer, Backend (AI Agent Runtime)
Salary not listed • Remote • Canada (Remote) • Full-time
Posted 1y ago
This job has been open for more than 60 days. It may no longer be actively hiring, so check with the company before putting a lot into an application.
About the job
Cresta is seeking a Senior Software Engineer to build and operate the real-time AI agent runtime infrastructure. This role involves designing and managing a low-latency system for voice and chat AI agents, including LLM streaming and conversation state management. You will also solve complex distributed systems problems related to session management, fault tolerance, and consistency. Additionally, you will develop a serverless-style function execution platform for custom customer logic, focusing on orchestration, container lifecycle, and autoscaling. A key part of this role is owning the developer experience, building tools like CLIs and local development environments to enable rapid iteration and confident shipping. You will also be responsible for raising the bar on production quality through observability, incident response, and best practices, and will be expected to operate the systems you build.
Responsibilities
- Design and operate a stateful, low-latency runtime for voice and chat AI agents, including LLM streaming and conversation state management.
- Solve distributed systems problems such as session management, affinity, checkpointing, crash recovery, and consistency.
- Build a serverless-style runtime for customers to deploy custom logic, including orchestration, container lifecycle, autoscaling, and versioned rollouts.
- Develop developer-facing tooling, including CLI tools, local development environments, and test execution frameworks.
- Drive observability, incident response, and engineering best practices for production quality.
- Operate the systems you build, including on-call rotations and incident response.
Requirements
- 5+ years of software engineering experience, with significant time spent on infrastructure, platform, or systems work.
- Proficiency in both Python and Go.
- Deep understanding of distributed systems concepts (consistency, fault tolerance, state management, concurrency).
- Experience with Kubernetes and cloud-native infrastructure.
- Experience building developer-facing tooling (CLIs, SDKs, internal platforms).
- Strong communication skills for driving technical decisions, writing design docs, and mentoring.
- High standard for code quality, including thorough testing and thoughtful code review.
- Comfort operating production systems, including on-call and incident response.
- Active use of LLMs and AI-assisted tools in daily development.
Benefits
- Medical, dental, and vision plans
- Paid parental leave
- Monthly Health & Wellness allowance
- Work from home office stipend
- Lunch reimbursement for in-office employees
- 3 weeks PTO in Canada
- Base salary
- Equity