Posted 13h ago

Cartesia Posted 30+ days ago
Software Engineer, Agent Harness
Location
San Francisco
On-site
Contract
Permanent
Full-time
Salary
$180–250k
Gross per year
Experience
Not specified
Job summary
Responsibilities
Cartesia builds real-time multimodal intelligence: fast, state-of-the-art voice models, and the platform that puts them into production. We started as a research lab, pioneered the state space model architecture, and now we're bringing that research to customers through Managed Agents, our voice…
- Evolve the realtime transport layer that carries audio between users and agents, expanding how customers connect across web, SDKs, and telephony without regressing latency or…
- Trace and cut end-to-end conversational latency across the STT, LLM, and TTS pipeline.
- Make agent deployments fast and resilient: faster cold starts, smarter scaling, graceful behavior under load.
- Define how voice agent quality is measured, building eval suites, LLM-as-judge scoring, and regression tracking that catch quality and latency regressions before they ship.
What they're looking for
- Experience building and operating distributed backend systems in production, ideally at a high-growth startup.
- Strong product instincts: you think in customer-facing latency, reliability, and developer experience, and you have opinions on what to build and why.
- Fluent use of coding agents and a habit of keeping pace with the frontier.
- Clear communication with technical and non-technical audiences, sharp specs, and a strong presence in design reviews.
Tech stack
Read the full job posting
This summary is written by Tokn from the original posting. Only the posting published by Cartesia is authoritative. Request a removal
Similar jobs
All LLM & GenAI jobs in San Francisco →Posted 16h ago
Posted 19h ago


