AI Engineer

A well-funded, high-growth Israeli cybersecurity startup pioneering the next generation of Identity Security and Governance platforms.

Backed by premier tier-1 venture capital funds following substantial funding rounds, the company was founded by serial entrepreneurs and elite technological unit alumni.

The company develops an enterprise-grade AI-powered platform leveraging state-of-the-art LLMs to manage, govern, and secure both human and non-human identities.

By continuously mapping complex identity graphs, entitlements, and access vectors, the platform eliminates attack surfaces and automates lifecycle operations.

Operating at the cutting edge of applied GenAI and autonomous agentic workflows, the engineering culture pairs high autonomy with technical rigor.

The office is located in Tel Aviv adjacent to major transit corridors and the light rail, operating on a hybrid model with one day working from home.

Role Description

• Serving as an AI / LLM Software Engineer, joining the core intelligence squad responsible for architecting and deploying the platform's advanced AI brain and autonomous agent layer.
• Driving applied GenAI workflows (~60–70% focus): advanced prompt orchestration, RAG architectures, semantic search, hybrid retrieval, and autonomous multi-agent systems.
• Implementing rigorous LLM production mechanisms: model evaluation frameworks (evals/benchmarks), human-in-the-loop validation, and mitigating LLM failure modes, hallucinations, and edge cases in production.
• Building robust backend pipelines and infrastructure (~30–40% focus): data pipelines, schema design, structured workflow orchestration, and end-to-end system architecture.
• Optimizing production AI systems for latency, inference cost, throughput, and comprehensive observability/monitoring.
• Developing core capabilities including an enterprise-grade natural language AI Assistant and proactive autonomous agents continuously analyzing large-scale identity graphs.

Requirements-

• Extensive hands-on software engineering experience in backend, AI, or data-intensive systems, with a proven track record of shipping production platforms serving active customers – Mandatory
• Proven hands-on experience deploying LLMs in production, including advanced prompting, tool use, function calling, orchestration, and evaluation, alongside a solid grasp of real-world failure modes – Mandatory
• Strong software engineering capabilities in Python (or equivalent modern languages) building scalable backend services with deep awareness of latency, multi-tenancy, and inference costs – Mandatory
• Strong end-to-end systems engineering skills: data pipelines, schemas, retrieval layers, production deployment, telemetry, and continuous monitoring – Mandatory
• Demonstrated ability to make sound architectural decisions, navigate ambiguity, and lead technical direction in high-impact initiatives – Mandatory
• Pragmatic, product-oriented builder mindset with a focus on ownership, rapid execution, and customer-driven problem-solving – Mandatory
• Excellent communication and alignment skills, with the ability to articulate complex technical trade-offs across teams – Mandatory