AI Agent Engineer  ON-SITE 

Location: New York, NY  |  Work arrangement: ON-SITE (in person 4–5 days per week in Manhattan)

Compensation: $200,000–$300,000 per year + equity  |  Employment: Full-time

Experience: 3–10 years  |  Visa sponsorship: none  |  Openings: 1

Our Ref: GEN-0002  |  Client Ref: X985R7VY

Company Confidential

About the Company

A fast-growing, YC-backed seed-stage startup (founded 2024) that uses generative AI to automate debt collection, a $35B US market. Its AI agents already outperform human collectors by 2x at a fraction of the cost, and they handle 10M+ calls a month. With a team of five, it reached a $2M annualized run rate within a few months and is targeting $10M ARR this year.

The Role

The company is building its voice AI agent infrastructure in-house and needs an AI Agent Engineer to own it end to end. You will build on LiveKit, design the orchestration layer, own the prompting strategy for millions of consumer interactions, and keep improving voice-agent performance through rigorous testing and iteration. It is a highly technical role for someone equally at home building production-grade systems and writing the conversational AI logic behind real-world outcomes. Deep voice-AI experience is ideal, but a strong infrastructure engineer who is analytical and business-minded is also a fit.

Key Responsibilities

• Build the voice AI infrastructure in LiveKit from the ground up
• Design and own the architecture of real-time voice-agent systems, including orchestration, state management, latency optimization, prompting, and reliability
• Own the end-to-end prompting strategy: conversation flows, tone, compliance-safe phrasing, guardrails, and edge-case handling
• Build and maintain testing and evaluation frameworks (A/B testing, regression testing, conversation QA, benchmarking, KPI reporting)
• Write, expand, and continuously improve prompting to cover more real-world scenarios
• Use 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 and tooling for millions of voice interactions, and migrate clients off legacy voice infrastructure while preserving their customizations
• Work with product, operations, and leadership to turn business goals into high-performing agent behavior

Requirements

• 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 an equivalent
• Strong prompt-writing instincts, with the ability to design clear, effective, resilient conversational flows
• Strong analytical skills, tying technical work directly to business outcomes and ROI
• Excellent written and verbal English (required for the prompt-engineering work)
• High ownership and a strong work ethic
• Based in NYC or willing to relocate; in person 4–5 days per week

Nice to Have

• SIP trunking, telephony infrastructure, and production voice systems
• Real-time audio pipelines, call routing, and carrier or telephony integrations
• Speech infrastructure in production environments
• Domain knowledge in debt collection, financial services, or regulated consumer communication

Interested? Apply for this role (Ref GEN-0002)