Full-Stack Engineer (AI)

YozmaTech isn’t just another tech company – we’re a global team of go-getters, innovators, and A-players helping startups and product companies scale smarter and faster.
We build dedicated development teams across 10+ countries, creating strong, long-term partnerships based on trust, transparency, and real impact.
Here, every idea counts. We value people who are proactive, open-minded, and ready to grow. If you’re passionate about building meaningful products and want to join a team that feels like family – you’ll feel right at home with us.

Our client is building a new product in the maritime intelligence space — helping governments and port authorities gain visibility into global shipping activity.
The platform analyzes vessel movements, cargo data, and risk signals to identify potential issues — including high-risk or non-compliant shipments — before they reach port.
It combines real-time data, rule-based logic, and predictive models to deliver actionable insights for decision-makers.
This is a new product built from scratch.
A prototype already exists, but the core architecture and product decisions are still open.
The team will work closely with senior engineering leadership based in Israel and will play a key role in shaping the product from early stage to production.

Requirements
🔹7+ years of professional full-stack engineering experience, including 2+ years of experience building agents or agentic workflows in production at scale within a distributed system architecture;
🔹Proven expertise building autonomous agentic systems using frameworks such as LangChain, LangGraph, DeepAgents, CrewAI,
OpenClaw, or Hermes (or able to demonstrate equivalent expertise on another relevant framework);
🔹Fluent in Python or TypeScript/Go/Rust, with proficiency in transitioning to Python;
🔹Experience with Frontend stack (NextJS, React.js, or similar);
🔹A solid background with the AWS stack, including Kubernetes (K8S), Terraform (IaC), and CI/CD is essential (Helm is a strong plus);
🔹Proficient in high-scale AI-based development, utilizing tools like Claude Code, Cursor, or Copilot in a highly autonomous fashion, and are a strong, independent individual contributor;
🔹English - Upper-Intermediate or higher.

What you will do:

🔹Architect & Build: Design and deliver agentic workflows and scalable microservices, primarily using Python, within a distributed system architecture;
🔹AI Integration: Lead the integration of Generative AI capabilities, including LLM APIs, RAG pipelines, and agentic workflows into our production systems;
🔹Implement operational practices, observability, and autonomous monitors (e.g., detecting intelligence drift or hallucinations) to ensure AI reliability in production;
🔹Drive overall engineering quality and speed by implementing AI-SDLC practices, ensuring high standards through rigorous code reviews, test automation, and by establishing continuous, trace-based quality evaluation for all software and agentic components;
🔹Evaluate emerging AI tooling, mentor fellow engineers, and contribute directly to our technical roadmap.

Interview stages:
🔹HR interview;
🔹Introductory Interview
🔹First Technical Interview
🔹Second Technical Interview
🔹HR Interview
🔹References;
🔹Offer.