← All roles

Software Engineer, Agent Harness

Cartesia· Engineering
Apply on company site
*HQ - San Francisco, CA$180k - $250kFull-timePosted 5mo ago

About the role

Role focused on building the platform behind Cartesia's real-time, multimodal voice agents (Managed Agents). You will own the stack end-to-end to shape latency, reliability, and developer experience for real-time production-grade voice agents.

Responsibilities

  • 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 quality.
  • 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.

Qualifications

  • Experience building and operating distributed backend systems in production, ideally at a high-growth startup.
  • Strong product instincts: customer-facing latency, reliability, and developer experience.
  • 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.

Skills

Required:Distributed backend systemsLatency optimizationDeveloper experience

Benefits

  • Competitive base salary alongside attractive equity package.
  • Fully covered medical insurance along with dental and vision for you and your family.
  • 9 weeks paternity & 12 weeks maternity leave
  • 401(k)
  • Commuter Allowance
  • Flexible PTO
  • Meals & Snacks, lunch and dinner provided daily.
Last updated Aug 26, 2026. Interested? Apply on the company site.

About Cartesia

Real-time TTS API with AI laughter and emotion

Cartesia offers Sonic-3, a streaming text-to-speech API capable of generating natural, expressive voices with laughter in 40+ languages—built for AI agents and interactive applications.

AI voicesinteractive appsliquid-ai-recruiting-targetmultilingualstreaming APItext-to-speechvoice-ai-stack
Company profileWebsite

More open roles at Cartesia