You are viewing a preview of this job. Log in or register to view more details about this job.

AI Agent Engineer

REWORK Digital
Email

 

We are looking for an AI Agent & Conversational Systems Engineer to own agent and chatbot engineering - one of the core service categories on the REWORK platform, and also the tooling behind Rezy, the AI guide that walks users through verification, matching, and the marketplace across the app, plus the AI receptionist product our Growth team demos to prospective clients. You will design multi-turn agents with tool use and retrieval, keep them grounded in REWORK's live product knowledge as categories and features ship, and build the same class of agents - support bots, lead-qualification bots, voice receptionists - as client-facing automations for businesses on AutoTeam. This role sits at the intersection of internal product AI and the automation practice we sell.

Core Responsibilities

 

Agent Design & Grounding

 

  • Design multi-turn conversational agents with tool use, function calling, and retrieval over live product knowledge
  • Keep Rezy and other in-app assistants grounded and accurate as categories, pricing, and features change
  • Architect RAG pipelines and vector search so agents answer from real, current data instead of stale prompts

Voice & Client-Facing Agents

 

  • Build and maintain the AI receptionist product - call handling, intake, and hand-off logic
  • Ship chat and voice agents as client deliverables: support bots, lead-qualification bots, internal knowledge bots
  • Integrate agents into WhatsApp, web chat, and voice channels with reliable session and state handling

Reliability & Iteration

 

  • Monitor conversation quality, escalation rates, and failure modes; ship fixes fast when an agent goes off-script
  • Version and test prompt/tool changes before they reach production traffic
  • Document agent architecture, tool schemas, and grounding sources so another engineer can extend the system

Required Qualifications

 

Required Experience

 

  • Shipped production conversational agents or chatbots with tool use and/or retrieval, not just prompt-only demos
  • 1+ years hands-on with the OpenAI or Anthropic APIs and at least one agent framework

System Design & Problem-Solving

 

  • Understands the failure modes of LLM agents - hallucinated tool calls, lost context, runaway loops - and designs against them
  • Comfortable debugging across the stack: prompt logic, tool schemas, retrieval quality, and latency

Documentation & Nice-to-Haves

 

  • Documents agent behavior, grounding sources, and escalation logic clearly
  • Nice to have: voice AI (Twilio/LiveKit), multi-agent orchestration, evals experience, SaaS / startup background

Key Deliverables

 

Rezy and internal assistants staying accurate as the product evolvesA reliable AI receptionist product ready to demo and deploy for clientsClient-facing agents shipped as REWORK automation deliverablesClear, well-documented agent architecture and grounding sources

Tech Stack & Skills

 

OpenAI Agents SDKAnthropic Claude APILangChain / LangGraphRAGVector DBs (Pinecone / pgvector)MCP / Tool UseFunction CallingTwilio / LiveKit (voice)Whisper / ElevenLabs / DeepgramPythonNode.jsWebSockets

Expectations

 

  • Work asynchronously in a remote-first environment (Slack, email, documented reports)
  • Operate highly independently - evaluated on proof-of-work and reliability of deliverables
  • Collaborate during core hours, 10:00 AM – 4:00 PM Eastern Time
  • Keep agent architecture, prompts, and tool schemas clear, well-documented, and easy to navigate