דרושים » AI » דרוש /ה AI Agent Engineer ברמת גן - היברידי (3 ימים מהבית) - קו רכבת

You'll work end-to-end: agent design, tool implementation, retrieval quality, integration into existing product UIs, cloud infrastructure, and evaluation/observability. The platform already ships to customers - you'll extend it, raise its quality bar, and help define where it goes next.

What you'll do

Design and evolve agents - build LLM agents with tool use, routing, and human-in-the-loop flows.
Implement tools and integrations - expose product capabilities to the agent, with multi-tenant context, via internal APIs and MCP servers.
Own retrieval quality - contribute to our RAG pipeline end-to-end: ingestion, embeddings, vector search, and reranking.
Define and evolve host integration contracts - collaborate with host application teams to integrate the assistant into product UIs built on different frontend stacks. You own the shared remote module and the integration API; host teams own their stacks.
Drive evaluation-led development - write evaluators (rule-based, LLM-as-judge, multi-turn), maintain CI eval gates, and use traces and feedback to debug production behavior.
Operate the platform - own deployments, observability, and the performance and cost of LLM-backed services.
Establish engineering practices** for AI-specific work: prompt versioning, eval coverage, testing, and code review.

We are seeking a hands-on technical leader to architect and lead the development of production LLM-based applications. This role will lead a cross-functional team of software engineers and data scientists and will own architecture, delivery, evaluation, observability, and production readiness.



The ideal candidate is a proven software leader who has delivered complex production-grade systems and can align engineering, data science, product, and platform work into one cohesive execution model. The role requires strong software architecture, applied AI judgment, disciplined execution, and people leadership, with a focus on turning ambiguous product goals and exploratory AI work into reliable production software.



Responsibilities:

Lead a cross-functional team of engineers and data scientists developing LLM-based applications.
Translate product and business goals into technical roadmaps, milestones, and deliverable plans.
Own end-to-end delivery from architecture and experimentation through deployment, monitoring, evaluation, and continuous improvement.
Design LLM workflows using RAG, tool calling, structured outputs, agents, deterministic logic, and human-in-the-loop patterns where appropriate.
Establish evaluation-driven development practices for LLM features.
Define quality metrics, regression tests, golden datasets, production feedback loops, and observability standards.
Ensure systems meet production standards for scalability, performance, reliability, security, and maintainability.
Provide technical guidance, architectural oversight, mentorship, and career development for team members.
Manage priorities, scope, risks, and trade-offs across multiple streams of work.
Partner with product, design, DevOps, data engineering, security, and other technical leaders.
Drive continuous improvement in delivery quality, engineering practices, and team effectiveness.