AI Software Engineer – Voice AI & Agent Systems (Part-time/ Internship)

πŸ“ Fully Remote (US preferred)

πŸŒ‰ Occasional team gatherings in the San Francisco Bay Area

About Us

We are building next-generation voice-first AI systems and intelligent agents.

Our founding team includes engineers and leaders from:

  • Apple Siri

  • Apple Vision Pro

  • Microsoft AI

  • SpaceX

We are:

  • πŸ† Winner of the UC Launch Accelerator – Audience Choice Award

  • πŸŽ“ Backed by the Berkeley Haas Seed Fund

  • ☁️ A Google Cloud Partner

We build real AI-native systems β€” not demos β€” at the intersection of voice, multimodal intelligence, and autonomous agents.

The Role

We are seeking a highly technical, product-driven AI Software Engineer with hands-on experience building production-grade voice AI and LLM agent systems.

This role requires real-world experience with:

  • Voice AI pipelines

  • LLM orchestration

  • Agent systems

  • Memory architecture

  • Latency optimization

You will work on core AI infrastructure powering a real-world intelligent system.

What You’ll Do

  • Design and implement real-time voice AI pipelines (STT β†’ reasoning β†’ action β†’ TTS)

  • Integrate and optimize LLM APIs (OpenAI, Anthropic, open-source models)

  • Build and deploy AI agents with:

    • Tool use / function calling

    • Multi-step reasoning

    • Planning + execution loops

  • Architect LLM memory systems

    • Vector databases

    • RAG pipelines

    • Context compression

  • Optimize latency for real-time conversational UX

  • Implement streaming architectures for live voice interaction

  • Experiment with frontier frameworks such as OpenClaw

  • Continuously track and evaluate emerging AI technologies

Required Qualifications

  • 1~3 years of software engineering experience

  • Production experience building LLM-powered applications

  • Experience orchestrating large model APIs

  • Experience building AI agents

  • Experience implementing LLM memory systems

  • Experience optimizing inference latency

  • Experience with voice AI systems (STT/TTS/streaming)

  • Strong Python skills

  • Cloud deployment experience (AWS/GCP/Azure)

  • Strong interest in frontier AI research and agent systems

Strong Plus

  • Experience with OpenClaw or OS-level agent automation

  • Multimodal AI experience (vision + language + audio)

  • Edge/on-device AI experience

  • Startup 0 β†’ 1 product experience

  • Hardware-integrated AI systems

Work Structure

  • Fully remote

  • Flexible schedule

  • Occasional in-person team gatherings in the San Francisco Bay Area

  • Competitive compensation + equity

  • We sponsor CPT / OPT candidates

If you’re excited about building frontier voice-first AI systems with a team that has shipped category-defining products, we’d love to talk.