11h ago

Software Engineer - Voice AI (Inference Runtime)

San Francisco

$165k-$330k / year

full-timesenior Hybridai-ml

๐Ÿ›  Tech Stack

๐Ÿ’ผ About This Role

You'll own Baseten Voice AI inference stack, bringing state-of-the-art open source models into production for Voice AI customers. You'll drive real-time, large-scale model serving for STT, TTS, and voice agents, impacting productivity, customer service, and healthcare. This role offers high ownership and cross-team collaboration.

๐ŸŽฏ What You'll Do

  • Own and lead Voice AI product areas end-to-end.
  • Design, build, and operate real-time model serving systems.
  • Drive cross-team collaboration on full-stack technical problems.
  • Mentor teammates through code reviews and design docs.

๐Ÿ“‹ Requirements

  • Bachelor's degree or higher in Computer Science or related field.
  • Proven track record owning production-grade real-time, large-scale systems with tail latency concerns.
  • Proficient coding in one or more programming/scripting languages (Python preferred).
  • Comfortable using AI coding assistants (e.g., Claude Code, Cursor) daily.

โœจ Nice to Have

  • Experience implementing pipeline-level model runtime optimizations (dynamic batching, async scheduling).
  • Experience building developer platforms (SDKs, CLIs, APIs) for ML or infrastructure.
  • Familiarity with speech/audio ML models (STT, TTS) and model-serving runtimes (vLLM, TensorRT).

๐ŸŽ Benefits & Perks

  • ๐Ÿ’ฐ Competitive compensation including meaningful equity.
  • ๐Ÿฅ 100% coverage of medical, dental, and vision insurance for employee and dependents.
  • ๐Ÿ–๏ธ Flexible PTO including company-wide Winter Break.
  • ๐Ÿ‘ถ Paid parental leave and fertility stipend through Carrot.
  • ๐Ÿ“ˆ 401(k) company-facilitated.

๐Ÿ“จ Hiring Process

Estimated timeline: 2-4 weeks ยท AI estimate

  1. 1Recruiter Screenยท 30 min
  2. 2Technical Phone Interviewยท 60 min
  3. 3Onsite (System Design + Behavioral)ยท 4 hours
0 0 0