LLM Engineer (AI)

An elite GenAI Startup led by successful serial entrepreneurs with a proven track record of scaling and exiting ventures. The company is architecting a disruptive AI platform designed to automate complex analytical workflows, saving massive resources for product and data teams.

Backed by significant funding, the organization offers the unique combination of "Day 0" impact with the financial stability to offer highly competitive compensation and equity.

Located in Tel Aviv (Next to a rain station), the company fosters a high-velocity, hybrid work environment (2 days WFH).

Responsibilities-

• Autonomous Agent Design: Architecting and deploying AI Agents featuring complex Reasoning chains, Tool orchestration, Planning loops, and long-term memory systems.
• Production-Grade AI: Building the engineering infrastructure around LLM agents, including Evaluation frameworks, Observability, and production monitoring at scale.
• Rapid Prototyping: Experimenting with cutting-edge LLM techniques and research to maintain the platform's competitive edge in a fast-paced environment.
• System Architecture: Taking full ownership of Backend performance, API design, and Microservices architecture to support autonomous task execution.

Requirements

• 5 years of Backend engineering experience, specialized in scalable distributed systems and Microservices – Mandatory.
• Minimum of 2 years hands-on experience building with LLMs in production, with deep expertise in Agentic workflows, function calling, and autonomous design patterns – Mandatory.
• Expert-level Python programming with strong software engineering fundamentals – Mandatory.
• Deep understanding of reasoning patterns, context window management, and strategies for ensuring reliable agent behavior.
• Proven experience with Public Cloud (AWS/GCP/Azure), RESTful APIs, and modern databases.
• A genuine passion for staying current with the evolving LLM landscape, research papers, and the AI engineering community.