AI Agent Engineer

Building its voice AI agent infrastructure in-house and needs an AI Agent Engineer to own it end-to-end. You’ll build on top of LiveKit, design the orchestration layer, own the prompting strategy for millions of consumer interactions, and continuously improve voice-agent performance through rigorous testing and iteration. A highly technical role for someone equally comfortable building production-grade systems and writing the conversational AI logic that powers real-world outcomes. Deep voice-AI experience is ideal; a strong infrastructure engineer who is analytical and business-minded is also a fit., * Design and own the architecture of real-time voice-agent systems: orchestration, state management, latency optimization, prompting, reliability

• Own the end-to-end prompting strategy: conversation flows, tone, compliance-safe phrasing, guardrails, edge-case handling
• Build and maintain testing/evaluation frameworks (A/B testing, regression testing, conversation QA, benchmarking, KPI reporting)
• Write, expand, and continuously improve prompting to cover more real-world scenarios
• Iterate on performance data and call outcomes to improve containment, conversion, liquidation rates, and satisfaction
• Optimize ASR, STT, TTS, turn-taking, interruption handling, and state transitions
• Build scalable systems/tooling for millions of voice interactions; migrate clients off legacy voice infra while preserving customizations
• Work with product, operations, and leadership to translate business goals into high-performing agent behavior

Artificial Intelligence (AI), Startup, Credit and Collections, Artificial Intelligence (AI), Analysis Skills, Continuous Improvement, Customer Relations, Performance Testing, Production Systems, Architectural Design, * 2+ years in voice AI, conversational AI, prompt engineering, speech systems, or related agentic workflows

• 3+ years in platform, infrastructure, or backend engineering
• Strong experience with Node.js, AWS, and SQL
• Experience building and shipping production systems in a startup or similarly fast-paced environment
• Experience with voice orchestration platforms or agent frameworks such as LiveKit or equivalent
• Strong prompt-writing instincts; designs clear, effective, resilient conversational flows
• Strong analytical skills; ties technical work directly to business outcomes and ROI
• Excellent written and verbal English (required for the prompt-engineering component)
• High ownership and strong work ethic
• Based in or willing to relocate to NYC; in-person 4-5 days per week, * SIP trunking, telephony infrastructure, and production voice systems
• Real-time audio pipelines, call routing, carrier/telephony integrations
• Speech infrastructure in production environments
• Domain knowledge in debt collection, financial services, or regulated consumer communication

A fast-growing, YC-backed seed-stage startup (founded 2024) using generative AI to automate debt collection - a $35B US market. Its AI agents already outperform human collectors 2x at a fraction of the cost, doing 10M+ calls per month. With a team of five, it scaled to a $2M annualized run rate in just a few months, targeting $10M ARR this year.