Staff Machine Learning Engineer

Zendesk Zendesk · Enterprise · Krakow, Poland +5 · Remote

Staff Machine Learning Engineer to enhance Zendesk's search platform, focusing on AI-powered capabilities, RAG bots, and hybrid search solutions. The role involves delivering AI features at scale, collaborating with cross-functional teams, mentoring junior members, and supporting deployed services. Key challenges include expanding the RAG platform, improving hybrid search (vector embeddings and keyword retrieval), enhancing search result ranking, optimizing indexing, and leveraging LLM technologies.

What you'd actually do

  1. Delivering AI-powered capabilities to our customers at Zendesk scale using latest LLM technologies
  2. Working closely with Product Management, ML Scientists and fellow Engineers both within the team and across the company to define feature scope and implementation strategies, using ML technology
  3. Mentoring junior team members, as well as pairing with more experienced colleagues to foster mutual learning
  4. Supporting our deployed services to ensure a high level of stability and reliability
  5. Writing clean and maintainable code to meet the team’s delivery commitments

Skills

Required

  • Proficiency in programming languages such as Python or Ruby
  • Experience in relevant testing frameworks
  • Solid understanding of architecture and software design patterns for server-side and web applications
  • Collaborative and growth mindset
  • Self-managed, dedicated approach with the ability to work independently
  • Experience building scalable and stable software applications
  • Ability to formulate hypotheses, conduct experiments, and analyze results to inform engineering decisions

Nice to have

  • Experience in designing, implementing, and optimizing search solutions, ideally leveraging Machine Learning techniques and Elasticsearch to enhance search relevance and performance
  • Experience with managing and deploying cloud services with AWS
  • Experience with event-driven, distributed architecture using Kafka

What the JD emphasized

  • RAG platform
  • hybrid search solutions combining vector embeddings and keyword-base retrieval
  • ranking of search results
  • indexing pipeline for speed and cost-efficiency
  • retrieval platform across multiple channels
  • rapidly evolving LLM technologies
  • leveraging Machine Learning techniques and Elasticsearch to enhance search relevance and performance

Other signals

  • delivering AI-powered capabilities at scale
  • expanding RAG platform
  • integrating and improving hybrid search
  • optimizing indexing pipeline
  • leveraging LLM technologies