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

We're looking for a Senior AI Engineer to design, build, and ship production-grade LLM agents that reason over workforce and skills data on top of Loomra's semantic layer. You won't just prototype - you'll own agent workflows end to end, from design through evaluation, deployment into the tools employees use daily (Teams, Slack, Copilot), and iteration in front of enterprise customers. You'll work alongside product, data, and platform engineers to turn powerful capabilities into reliable, safe, and fast product experiences.
If you've built agents that actually made it to production - and you care as much about evaluation, guardrails, and reliability as you do about capability - we want to talk to you.
Responsibilities
Design and build multi-agent systems and orchestration - intent routing, planning, tool use, and coordination across specialized agents.
Implement retrieval and RAG pipelines over structured and unstructured workforce data, grounded in our knowledge graph connecting people, jobs, and skills.
Integrate LLMs with tool/function calling and protocols such as MCP to give agents controlled access to HCM systems, business logic, and workflows.
Build evaluation harnesses, guardrails, and safety/bias checks, and work within the governance engine so agents behave reliably, respect customer policies, and produce a full audit trail.
Ship agents in a model-agnostic way across providers (Anthropic, Google, IBM watsonx) and deploy them into Teams, Slack, and Copilot.
Optimize agents for latency, cost, and reliability at enterprise scale.
Take agents from prototype to production - with monitoring, observability, and a fast iteration loop.
Partner closely with product, data, and platform teams to translate customer needs into agent capabilities.

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.