Required Senior AI-Native Software Engineer
Role summary:
You will join a high-impact AI engineering team within R&D, owning problems end-to-end from understanding the business need, through architecture and implementation, to production monitoring. This is a new way of working: you'll work directly with business stakeholders, ship AI-driven capabilities at speed, and help define the methodology as we build it.
As a member of the AI Foundations organization, you will lead best practices, champion early adoption of new technologies, and influence the direction of our R&D guild - building and shipping cutting-edge agentic applications that deliver seamless experiences to our users.
Location:
Hybrid - Herzliya, Israel
Full-time
What you'll do:
Own the full development loop understand the business problem, define the solution, architect it, build it, ship it, and monitor it in production
Use AI as your primary development tool, achieving in a day what used to take a team a week
Collaborate with your team and business stakeholders to define decision logic, risk thresholds, and success metrics
Design and build evaluation frameworks as part of every solution you don't ship what you can't measure
Own production readiness monitoring, alerting, and observability go in on day one
Contribute to shaping team practices, tooling, and engineering standards across the pod
Decompose business problems into agentic workflows, orchestrated flows, and reusable capabilities.

We are looking for a software engineer with strong backend skills, a product mindset, and the curiosity to bring LLM-powered agents into the toolchains and Linux environments where chips are actually designed. Success in this role means owning the agentic infrastructure end-to-end: from the platform our agents run on, to the integrations that let them safely act inside our customers' existing flows.
Description
You will join a growing team of ML and software engineers building GenAI solutions for chip design teams. In this role, you will:

* Architect, build, and operate the agentic infrastructure our team relies on:including LLM orchestration, tool-calling layers, multi-agent workflows, and the services that host them.
* Design and implement software solutions for chip design engineers, translating their workflows into reliable, automated agent-driven systems.
* Integrate our agents and services with existing Linux-based environments, in-house tools developed by the team, and third-party EDA tools.
* Manage agentic and ML workflows in production to ensure performance, high availability, and resource efficiency.
* Deploy and maintain production services, with proactive monitoring to catch quality and infrastructure regressions before they reach users.
* Build automated evaluation frameworks to measure retrieval quality, agent execution, and LLM output accuracy across releases.
* Partner with CAD teams to integrate pipelines and agents into CI/CD, ensuring reliable deployments and safe rollbacks.
* Implement access controls, authentication, and secret-handling practices appropriate for working with sensitive design data.
* Collaborate closely with ML engineers, researchers, and our customer teams.

We're building AI to tackle one of the hardest operational challenges in business: getting workforce management right across many markets, each with its own tax rules, labor laws, payment rails, and constantly shifting policies.
In this role on our AI team, you'll focus on agentic workflow automation. You'll design, build, and deploy reliable AI agents that automate complex HR, payroll, and payment workflows, handling decision-making, document intelligence, and complex tasks that typically require human judgment.
What You'll Do:
Design and build agent-based systems that automate document processing, business insights, and complex enterprise workflows
Build observability, evaluation, and feedback loops for agent behavior to improve reliability, accuracy, and trust in production
Own the technical architecture and engineering standards for agentic systems
Build or manage data pipelines to process large volumes of documents and unstructured data
Collaborate with domain experts to identify high-value automation targets and deliver end-to-end solutions
Stay current on agent frameworks, LLM capabilities and limitations, and apply emerging patterns pragmatically in production

We're building AI to tackle one of the hardest operational challenges in business: getting workforce management right across many markets, each with its own tax rules, labor laws, payment rails, and constantly shifting policies.
In this role on our AI team, you'll build and scale core AI systems that power products. You'll work across agentic document intelligence, autonomous agents, compliance AI, and ML-powered insights, prototyping quickly, building robust evaluations, and shipping production-grade AI with real business impact.
What You'll Do:
Build and ship AI/ML solutions using LLMs, agents, RAG, and document understanding models, alongside classic ML
Prototype quickly, validate feasibility, and turn strong POCs into production systems
Evaluate models and architectures, apply testing and guardrails to improve agent and service reliability
Research and apply emerging techniques: multimodal/document AI, agentic frameworks, synthetic data generation, and new architectural approaches
Work cross-functionally with product, R&D, and compliance teams to deliver end-to-end solutions
Contribute to scalable, secure architecture and engineering best practices for AI delivery