AI Product Builder

About Us

Linnovate Technologies is a leading open-source innovation company based in Bnei Brak. Since 2006, we have been dedicated to providing software solutions to enterprises. Our philosophy revolves around empowerment through open-source collaboration.

At Linnovate, we help organizations harness automation, data-driven insights and conversational AI to improve efficiency and customer engagement. Our AI projects combine low-code tools like n8n, custom chatbots, LLMs and cloud-based data services to deliver real-world impact for large enterprises.

About the Role

You will design, build, test and continuously improve LLM-based agents and agentic workflows – from prompts, tools and indexed knowledge sources to evaluation sets, quality metrics and production monitoring. You will work closely with developers, data engineers and clients to turn business processes into agents that work reliably in the real world.

We are looking for an AI Product Builder to join our team – an AI-savvy, analytical and curious person who has already built agents hands-on and knows that an agent is only as good as the way it is evaluated.

This is a full-time, hybrid role located in our office in Bnei Brak.

What You'll Do

•   Build AI agents and agentic workflows with n8n, LLM APIs and other low-code tools – defining agent instructions, tools (tool/function calling, APIs, MCP), knowledge sources (RAG) and multi-step logic over enterprise data.

•   Index and process data for agents: ingest, parse, clean and enrich enterprise content (documents, PDFs, web pages, databases, APIs), design chunking and metadata strategies, generate embeddings and build vector / hybrid search indexes – and keep them fresh as source data changes.

•   Optimize retrieval quality: measure and improve how well agents find the right information (recall, precision, relevance) by tuning indexing, chunking, filters and re-ranking.

•   Evaluate agents systematically: build evaluation sets and golden datasets from real business scenarios, define success criteria and quality metrics (accuracy, groundedness, task completion, tone, safety), and run automated (LLM-as-a-Judge) and human evaluations.

•   Iterate based on evidence: compare prompts, models and agent configurations against the eval set, run regression tests before every release, and report quality results to the team and to clients.

•   Deploy and monitor agents in production: trace agent runs, track accuracy, hallucinations, latency, cost and usage, and turn real-world failures into new test cases.

•   Perform data analysis with SQL and Python / JavaScript to understand client processes, find automation opportunities and analyze agent performance.

•   Document agent designs, evaluation methodology, decisions and test results clearly, in both English and Hebrew.

Requirements (Must-Have)

•   Hands-on experience building AI agents or LLM-based applications (professional, academic or personal projects) – e.g., tool calling, RAG, multi-step workflows or chatbots connected to real data.

•   Experience evaluating LLM / agent outputs: creating test sets, defining quality metrics, comparing prompt or model versions and analyzing failures.

•   Strong knowledge of data indexing and processing: data ingestion and parsing, text cleaning, chunking, metadata, embeddings, vector databases and hybrid / semantic search.

•   1+ years of experience in data analysis, business analytics, automation or AI development.

•   SQL capabilities.

•   Familiarity with Python or JavaScript scripting for data manipulation and API interaction.

•   Solid understanding of LLM concepts (prompting, context windows, hallucinations) and machine learning fundamentals.

•   Excellent communication and documentation skills in English and Hebrew.

Nice to Have

•   Big advantage: experience with agent applications and knowledge management systems – building, implementing or integrating agent platforms and enterprise knowledge bases (e.g., SharePoint, Confluence, Notion, enterprise search).

•   Experience with agent frameworks or SDKs (e.g., LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK) or with MCP.

•   Experience with LLM evaluation and observability tools (e.g., Langfuse, LangSmith, Promptfoo, Ragas, DeepEval, Arize).

•   Experience using or configuring low-code automation tools (preferably n8n, Zapier, or Make).

•   Bachelor's degree in Data Science, Computer Science, Statistics, or a related field.

•   Experience in data visualization (e.g., Power BI, Tableau, or Grafana).

•   Knowledge of version control (Git) and collaborative project tools (Jira).

•   Prior experience working in a consulting or client-facing environment.

What We Offer

•   The opportunity to work on innovative AI agent projects with diverse enterprise clients.

•   Continuous learning and development in the AI and automation space.

•   A flexible hybrid work environment.

•   A collaborative, supportive, mission-driven culture.