Agentic AI Researcher (AI)

TL;DR

Agentic AI Researcher (AI): Designing and developing production-grade agentic systems to automate end-to-end workflows across business functions with an accent on tool use, long-horizon reasoning, and multi-agent coordination. Focus on building robust evaluations, guardrails, and observability for non-deterministic LLM-based applications.

Location: Onsite in Tel-Aviv

Company

Pioneering automated vehicle inspection systems using advanced AI and computer vision to redefine vehicle safety and reliability globally.

What you will do

• Design and develop production-grade agentic systems to automate complex business workflows.
• Research and apply state-of-the-art techniques in planning, memory, and multi-agent coordination.
• Build robust evaluations, guardrails, and observability to ensure agent safety and performance.
• Collaborate with function owners to identify high-leverage automation targets and quantify impact.

Requirements

• 4+ years of industry experience building production ML/AI systems.
• 1+ year of dedicated experience with LLM-based or agentic applications.
• Strong software engineering skills in Python and familiarity with frameworks like LangGraph or DSPy.
• Hands-on experience with prompting, fine-tuning, and retrieval-augmented generation (RAG).
• Proven experience designing rigorous evaluations for non-deterministic systems.
• M.Sc. or Ph.D. in Computer Science, Electrical Engineering, or a related field is a strong advantage.

Nice to have

• Publications or patents in the field of LLMs and agents.
• Contributions to open-source projects related to AI/LLM frameworks.

Culture & Benefits

• Opportunity to harness cutting-edge technologies in AI and computer vision.
• High-visibility role within the CTO's office with direct company-wide impact.
• Rapid career growth within a fast-growing global team.
• Collaborative environment focused on innovation, excellence, and teamwork.