Zendesk
Zendesk
Zendesk dezvoltă software pentru servicii de relații cu clienții și vânzări, care ajută organizațiile să gestioneze conversațiile, solicitările de asistență și relațiile cu clienții într-un mediu conectat. Platforma sa reunește mesageria, chatul live, instrumente de automatizare bazate pe inteligență artificială, soluții pentru confidențialitatea și protecția datelor și un spațiu de lucru pentru agenți, oferind echipelor modalități flexibile de a-și organiza operațiunile de servicii pe măsură ce se dezvoltă. Zendesk oferă, de asemenea, servicii profesionale și resurse de instruire, punând un accent declarat pe interacțiuni personalizate cu clienții, fluxuri de lucru integrate, diversitate și incluziune și sustenabilitate.

Senior Machine Learning Engineer, AI Agents

Advance AI agent planning, memory, evaluation, and safety for Zendesk’s customer service resolution platform. Build reinforcement learning systems using production trajectories.

Descriere

  • Design memory structures and autonomous learning methods for AI agents.
  • Improve agent architecture through ambiguous goal decomposition, memory tier management, selective skill acquisition, and A2A-based multi-agent delegation.
  • Build customer service agent models with reinforcement learning on production trajectories.
  • Lead reinforcement learning infrastructure, including reward curricula, rollout systems, and feedback loops.
  • Develop multi-turn evaluations and automated trajectory analysis.
  • Add CI quality gates and regression detection to prevent deployments when agent performance declines.
  • Implement enterprise guardrails with supervisor patterns, capability-based access controls, and output validation.
  • Collaborate with colleagues in Zendesk’s hybrid work environment.

Cerințe

  • At least five years of experience building production machine learning or AI systems.
  • Practical experience with agent architectures, including planning, tool dispatch, memory, and error recovery.
  • Strong evaluation judgment and experience creating internal evaluations.
  • Fluency in Python and PyTorch.
  • Familiarity with at least one agent framework.
  • Sound judgment about when to build custom solutions.
  • Reinforcement learning experience or substantial expertise with language models is optional; relevant areas include reward shaping, online and offline tradeoffs, and using reward hacking as a diagnostic signal.

Beneficii

  • Hybrid work with the flexibility to work remotely for part of the week.
  • An inclusive workplace.
  • Reasonable accommodations for applicants with disabilities and disabled veterans.

Locuri de muncă similare

Titan Wealth Holdings

Regional Client Services Manager

Titan Wealth Holdings

Lead regional client service teams at Titan Wealth, a UK wealth management business. Oversee managers, operations, compliance and service improvements across multiple offices.

Deschide
Philips

Clinical Study Manager, Medical Devices — Pennsylvania Remote

Philips

Lead compliant medical device clinical studies for Philips, coordinating sites, documentation, data quality, budgets, and regulatory readiness. This remote role requires local proximity to Pittsburgh, Pennsylvania.

Deschide