Apply Edge Start your job search

AI Engineer

Gotfriends · Tel Aviv District, Israel

Apply & track with Apply Edge

An early-stage, well-funded Israeli startup pioneering autonomous Agentic AI and Customer Experience (CX) Automation platforms.Backed by prominent venture capital funds, the company is actively expanding its elite founding engineering squad to build next-generation, AI-native automation engines.The platform democratizes enterprise-grade autonomous intelligence, deep personalization, and real-time execution for growing mid-market businesses without the friction of legacy software or prohibitive enterprise costs.The engineering environment centers on cutting-edge LLM orchestration, multi-agent frameworks, and high-throughput real-time streaming architectures.The office is located in Tel Aviv directly adjacent to the light rail station, operating on a hybrid model with one day working from home.Role Description-Serving as a Founding AI / ML Systems Engineer, playing a central architectural role within the core engineering squad to design, build, and scale production-grade Agentic AI systems.Architecting and deploying end-to-end LLM reasoning pipelines, multi-model workflows, and multi-agent coordination frameworks for high-volume, real-time automation.Engineering robust streaming inference engines, prompt management layers, dynamic tool-calling mechanisms, and memory retrieval pipelines.Building and scaling high-availability, low-latency backend microservices and data pipelines in Python within AWS environments.Moving advanced generative AI architectures from experimental prototypes into resilient, observable, and cost-efficient Production environments.Collaborating closely with Founders, Product Managers, and Backend Engineers to define product capabilities and implement foundational AI engineering best practices.Requirements-B.Sc. in Computer Science, Software Engineering, or an equivalent technical degree from a recognized academic institution, OR an elite technological background from IDF tech intelligence units – Mandatory6+ years of hands-on experience in Backend Engineering, Machine Learning Engineering, or AI Systems Development – MandatoryProven, direct experience designing and shipping LLM / Generative AI systems directly in Production at scale – MandatoryAdvanced, hands-on programming mastery in Python – MandatoryDeep, practical expertise across modern LLM paradigms: streaming inference, prompt engineering/management, context caching, and multi-agent system design – MandatoryExtensive hands-on experience with agent orchestration frameworks, such as LangGraph, LangChain, or equivalent orchestration runtimes – MandatorySolid experience architecting and deploying distributed cloud services on AWS (or GCP) – MandatoryProven background operating within fast-paced Startup (SU) environments – MandatorySelf-directed mindset, strong system architectural thinking, and fluent English communication skills – Mandatory