Worth applyingClickUp · United States

Senior AI Engineer - Multi-Agent Frameworks

Skills and tasks

Suggested skills

  • Multi-agent state machine design and deadlock resolution
  • LLM evaluation and metric curation (Evals)
  • Enterprise privacy and tenant boundary enforcement in RAG

Skill-to-task connections are not available yet.

Tasks from the posting

  • Maintain agent creation platform

    You + AI

  • Integrate multiple LLMs

    AI does it

  • Build LangGraph workflows

    You + AI

  • Implement agent evaluation frameworks

    Your edge

  • Incorporate AI research advancements

    Your edge

  • Collaborate cross-functionally

    Your edge

  • Address AI privacy scenarios

    Your edge

  • Integrate platform search capabilities

    You + AI

Prepare for this role

Practice an interview or plan your next steps with AI Coach.

Interview prepPlan with AI Coach
Application and training
Apply with AI

Interview prep includes this job. AI Coach opens with a draft question. Apply with your existing resume

More analysis and source details
31%
of this job is already automatable.
69% is classified as human or shared work.
1 AI does it3 You + AI4 Your edgeof 8 duties

Your edge · 3 things

  • Architecting state management and recovery strategies for multi-agent workflows executing complex graph transitions.
  • Designing robust evaluation harnesses to monitor emergent behaviors and failure modes across heterogeneous LLMs.
  • Enforcing strict compliance boundaries, data anonymization, and tenant isolation across enterprise search tools.
The fieldgrowing · 5-7 years

Enterprise software demand is actively shifting toward multi-agent orchestration and dynamic workflow execution platforms. Engineering talent capable of resolving agent drift, cascading hallucinations, and distributed state coordination commands strong industry capital investment.

Do this week

  1. Multi-agent state machine design and deadlock resolutionDirectly determines your ability to build production-stable agent graphs that do not spin out into infinite execution loops.
  2. LLM evaluation and metric curation (Evals)Quantifying non-deterministic system performance is the primary barrier separating enterprise-ready platforms from experimental prototypes.
  3. LangSmithDebugging multi-agent coordination and tracking pipeline latency across LangGraph workflows.

Scan another job

Scan another job
8 of 8 duties traced to the posting ·How scoring worksBrowse other scans

Hiring for a role like this? See how teams use scans to write clearer job posts.