Senior AI Engineer — Conversational Voice AI

SmartAdvocate is seeking a Senior AI Engineer to build and operate enterprise-grade conversational voice AI agents for legal case intake and client calls. The role focuses on production ownership, telephony integrations, and reliable write-back of call results into case files with safety, monitoring, and audit readiness.

Responsibilities

• Architect, build, and deploy conversational voice agents that interact with callers, leads, and clients.
• Integrate conversational systems with VoIP/SIP and cloud communications platforms including Twilio, Plivo, Amazon Connect, and LiveKit, supporting topologies such as call forwarding, conferencing an agent onto a live call (including onto an SA number), and full number porting so the solution works with any firm phone system.
• Address live-call realities such as barge-in and turn-taking, interruptions, poor reception, accents, background noise, and graceful degradation when confidence drops.
• Optimize real-time STT, TTS, NLU, and latency budgets; select and tune voices for naturalness.
• Design warm transfer and escalation flows, including handing off to a human with full context and identifying high-value or urgent situations for immediate routing.
• Build real-time pipelines that transcribe, parse, and structure call conversations to populate case fields, create intake records, update case notes, and trigger downstream workflows automatically.
• Record and summarize every call into the case file with clear provenance for any information the agent entered.
• Detect the caller’s language and respond in it, with Spanish as the first priority after English.
• Design caller identification and authentication before any case information is disclosed, using more than caller ID alone.
• Make agent behavior configurable per firm, including operating hours and after-hours coverage, outbound calling windows by callee type and time zone, escalation rules, and voice selection.
• Implement guardrails, fallbacks, structured logging, and call/transcript retention that supports audit requirements.
• Own the service in production, including latency budgets, monitoring, alerting, failover, and on-call responsibilities, given the availability-critical nature of a law firm’s main phone line.

Requirements

• Demonstrable production experience building conversational voice agents integrated with telephony infrastructure such as SIP/RTP, WebRTC, Twilio Media Streams, LiveKit, Deepgram, ElevenLabs, Vapi, Retell, or similar.
• Real-time audio pipeline engineering experience including streaming STT and TTS, sub-second response handling, concurrency, and latency profiling under load.
• Pipeline engineering experience for extracting structured JSON or database payloads from live audio streams.
• Strong Python service development (FastAPI/async or equivalent) and clean REST API design.
• Production-ready LLM integration including function/tool calling, structured outputs, prompt and context engineering, and cost and latency tuning.
• Experience with event-driven and asynchronous patterns such as queues, background workers, retries, and idempotency.
• Ability to evaluate conversational quality systematically through test suites, transcript review, and regression testing when prompts or models change.
• Production ownership experience with containerized deployment, CI/CD, monitoring, structured logging, and having personally debugged a live outage.

Technologies

• VoIP/SIP, Twilio, Plivo, Amazon Connect, LiveKit
• SIP/RTP, WebRTC, Twilio Media Streams
• Deepgram, ElevenLabs, Vapi, Retell
• STT, TTS, NLU
• FastAPI, Python, LLM, JSON, REST API, CI/CD, queues

Benefits

• Salary Range: $120,000.00 - $160,000.00 (yearly)
• Comprehensive benefits package
• 401(k) and 401(k) matching
• Dental insurance, Health insurance, Health savings account, Vision insurance, Life insurance
• Flexible spending account
• Paid time off and Parental leave
• Reports to the CTO; works closely with the existing AI Architect and AI development team
• Location: Remote (US) or Hybrid in Melville NY
• Opportunity to lead high-impact AI work on an established platform with real customers and real data

Location and Salary

Location: Remote (remote)

Salary: USD 120,000 - 160,000 per yearly

How We Hire

• Resume and portfolio review
• A 45-minute conversation about systems you have built and operated
• A short technical exercise using a realistic problem from the actual domain (not a whiteboard puzzle)
• A final conversation with the CTO and the AI team