Senior Backend Engineer - AI Team - Paradox

Workday Workday · Enterprise · Tel Aviv, Israel

Senior Backend Engineer to architect and build production systems for LLMs at scale, focusing on high-performance services, reliability, and observability. The role involves bridging AI research and production, designing LLM evaluation frameworks, and understanding product challenges.

What you'd actually do

  1. Design and implement high-performance backend services and APIs that power Paradox’s core AI products.
  2. Bridge the gap between AI research and production-grade software, focusing on latency, reliability, and observability.
  3. Promote engineering standards through rigorous code reviews, architectural design, and best practices in distributed systems.
  4. Design and implement LLM evaluation frameworks to assess and integrate new AI models into real-world production flows.
  5. Deeply understand product challenges to make intelligent and efficient software-building decisions.

Skills

Required

  • 6+ years of hands-on experience in backend software development, focusing on building complex, distributed systems.
  • Proven Expertise in Python and modern backend technologies/API design.
  • Direct experience in developing LLM-based products (Agents, RAG, etc.) within production environments.
  • Strong System Architecture design skills, with experience in cloud-based environments (AWS/GCP) and CI/CD flows.
  • Database Mastery: Deep knowledge of both relational and non-relational databases.
  • Engineering Quality: Strong understanding of automated testing at all levels of the testing pyramid and Clean Code principles.
  • Technical Leadership: Proven ability to lead technical designs, collaborate across teams, and mentor junior engineers.
  • Fluent in English, including both written and verbal communication.
  • Authorization to work in Israel.

Nice to have

  • Experience with specialized AI infrastructure (Vector Databases, LLM Observability tools).
  • Experience with Conversational AI or complex Dialogue Management systems.
  • Familiarity with MLOps practices and monitoring LLM performance in production.
  • Background in Data Science or Data Engineering.

What the JD emphasized

  • Direct experience in developing LLM-based products (Agents, RAG, etc.) within production environments.
  • LLM evaluation frameworks

Other signals

  • Deploying LLMs at scale
  • Integrating AI capabilities into backend architectures
  • Building production systems for LLMs