AI Engineer

A highly successful Israeli Business-to-Developer (B2D) startup that designs an advanced, real-time cloud resource management engine for containerized infrastructure environments.

Backed by a substantial Series C round, the company’s platform autonomously optimizes cloud resource utilization, slashing compute costs while significantly boosting performance.

Supported by an elite engineering core comprising top tech veterans from premier intelligence units and high-growth unicorns, the company serves an impressive roster of leading enterprise clients and is experiencing rapid market expansion.

The company operates out of a modern facility in a central business district of Tel Aviv (highly train-accessible) and operates on an in-office work model.

Key Responsibilities-

• Writing robust, highly efficient, and maintainable server-side production code using Python.
• Designing and implementing autonomous AI Agents, Agentic systems, and state-machine orchestration layers to handle complex procedural workflows.
• Constructing and tuning high-performance RAG patterns, custom prompt-engineering architectures, and semantic context search engines.
• Setting up, connecting, and optimizing Vector Databases alongside unified protocol layers (such as MCP) to ingest multi-source context metadata.
• Monitoring, profiling, and debugging live AI application pipelines to guarantee low inference latency, high stability, and reliable system responses.
• Technical Stack Python, LLMs, AI Agents, Agentic Systems, LangGraph, LangChain, RAG, Model Context Protocol (MCP), Vector Databases, and Multi-Agent Systems.

Requirements

• 3 years of professional software engineering experience dedicated to Backend development or AI systems engineering (Mandatory).
• Comprehensive hands-on programming mastery and deep structural command utilizing Python (Mandatory).
• Proven technical experience designing, implementing, and deploying Generative AI systems or LLM-driven applications (Mandatory).
• Practical track record of building and scaling AI or Machine Learning components directly within high-volume Production environments (Mandatory).
• Deep architectural understanding of modern orchestration libraries (e.g., LangGraph, LangChain) or Vector Database management is a highly significant professional advantage.
• Exceptional technical agility, sharp problem-solving capabilities, and the independent drive to engineer production-ready AI products within an elite technical group.