Generative AI Engineer

Description

ONE ZERO is Israel’s fully digital, branchless private bank—created to bring private-banking level service to a broader public through advanced technology, automation, and AI led by Prof. Amnon Shashua. Building on this mission, we’re developing Ella—our GenAI “banking copilot”—to make money management simpler and more proactive, turning complex financial moments into clear, personalized insights while maintaining the trust, safety, and rigor expected from a regulated bank.

Ella (Tech): A GenAI agent embedded in ONE ZERO’s product flows and banking systems—not a chatbot bolted on—providing 24/7, multilingual help and daily “financial check-ups” that scan accounts and cards to flag anomalies, double charges, and savings opportunities.

Under the hood, we run an agentic, graph-based workflow (stateful orchestration) on top of leading LLMs: intents route through retrieval and verification steps, then into a typed actions/tool layer that can query live banking data and drive in-app workflows.

Why join: A rare chance to ship real, high-impact AI in a high scale production environment—with serious AI/engineering challenges in safety, and reliability, and daily “real-world” edge cases to solve.

Your Day-to-Day

• Build multi-agents and integrate them into product flows.
• Add evals, monitoring, and safety mitigations
• Collaborate with cross-functional teams to understand business requirements and translate them into technical solutions.
• Optimize and fine-tune Generative Agents for performance and scalability.
• Stay up-to-date with the latest industry trends and advancements in Generative AI Industry.
• Optimize inference performance, including latency, resource usage, and throughput, while maintaining model quality.

Requirements

• B.Sc/ M.Sc. degree in Computer Science, Software Engineering, or a related technical field - a must.
• AI-native development mindset: ability to use AI across the full software lifecycle (planning/design, implementation, testing, refactoring, maintenance) while keeping high standards for architecture, quality, security, scalability, and reliability.
• Proficiency in Python and LLMs- a must.
• 3+ years of hands-on experience integrating GenAI/LLM capabilities into production applications, including strong prompt engineering and prompt optimization techniques - a must.
• Experience developing NLP models at scale, from inception to production, with business impact.
• Experience with building multi-agents with GenAI libraries and tools, such as LangChain, LangGraph, and Multi-Agent systems.
• Experience with cloud platforms (AWS/GCP/Azure) and containerization (Docker, Kubernetes).
• Skill set includes software engineering, data infrastructure, and familiarity with RDBMS/NoSQL.
• Strong problem-solving skills with the ability to translate business requirements into scalable technical solutions.
• Exhibit robust problem-solving skills, with the capability to identify business challenges, formulate data-driven hypotheses, and design experiments to test and validate these hypotheses.

Advantages

• Experience building real-time, high-throughput AI applications at scale.
• Classic ML/NLP background, including deploying models at scale.