Member of Technical Staff, Platform

Ciridae • San Francisco, CA

4d

About The Position

You build the systems behind the systems. Every Ciridae customer deployment runs on the platform you maintain - the leverage of your work compounds with every new engagement. This is the role for engineers who would rather solve the hardest infrastructure problem once than the same problem six times. The hard problems behind running production AI across many live customer environments at once. Multi-tenant infrastructure, reliability and cost controls for non-deterministic systems, evaluation and observability where the ground truth keeps moving, and the internal tooling that turns what we learn on the ground into leverage for the next deployment. The questions a seed-stage team would normally postpone - we answer them now, because we have to.

Requirements

• Deep systems engineering experience.
• Distributed systems knowledge.
• API development experience.
• Database expertise.
• Cloud infrastructure knowledge.
• Expert Python skills.
• Terraform experience.
• GCP experience.
• Containerization experience.
• Multi-tenant production experience.
• Understanding of LLM-specific infra problems (model routing, evals, cost and latency controls).

Nice To Haves

• Go or TypeScript a plus.

Responsibilities

• Build the systems behind the systems that run customer deployments.
• Maintain the platform for production AI across many live customer environments.
• Address multi-tenant infrastructure challenges.
• Implement reliability and cost controls for non-deterministic systems.
• Develop evaluation and observability solutions for moving ground truth.
• Create internal tooling to leverage learnings for future deployments.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed