Back to jobs

AI Engineer - Agentic Products

Pay
Pay not listed
Work setting
Not stated
Employment
Not stated

About Guidde

Guidde is an AI digital adoption platform that serves as the creation and consumption hub for modern organizations.

In the employer’s words · Read in context

Apply at Guidde

Posting record

Report an error
Status in our records
Live
First seen by us
Nov 3, 202618 days ago
Recorded sightings
9
Last seen by us
Nov 21, 2026

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

How this job compares

Time since we first saw it

Day 18

Up longer than most. Similar jobs usually come down between day 1 and day 15.

From 1,368 similar postings that came down. Coming down is not always a hire.

Guidde is hiring

1 open job

Open jobs by the week we first saw them, last 12 weeks.

Hiring record

See how this role fits your experience

Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.

  • TypeScript
  • Node.js
Where the posting names them
What will you need to have? - 4+ years of production engineering, with strong TypeScript/Node.js - At least one LLM or agentic feature shipped to external customers and owned after launch - you can tell us what broke and how you found out

Your next step

Complete your application on job-boards.eu.greenhouse.io. The employer’s form will show what is required.

Applying through Greenhouse

  • No account needed: the form is one page, with an “Autofill my application” option that reads your resume.
  • Greenhouse doesn’t read resumes over 2.5 MB, or details placed in a header, footer, text box, table or second column. The file still attaches, but a recruiter has to type you in by hand.

Already applied? Track this application

Job description

View original posting ↗

About Guidde

Guidde is an AI digital adoption platform that serves as the creation and consumption hub for modern organizations. Founded in 2020 by seasoned entrepreneurs, we use generative AI to transform workflows into rich, multi-format documentation in minutes. Our platform helps teams scale knowledge across employees, customers, and even AI systems, turning everyday processes into instant, in-app video guiddes that live where work actually happens.

More than 5,500 organizations worldwide, from fast-growing startups to Fortune 500 enterprises, rely on Guidde to reduce support load, accelerate onboarding, and make knowledge accessible on demand. We’re building the future of how knowledge is created, shared, and experienced.

The Ideal "Guidder" is like our platform - clear, impactful, and focused on delivering value. We blend a startup environment with sports team principles - strategic in planning, collaborative in execution, and obsessed with customer wins. We value doers who listen more than they talk and who show up ready to play their best game. Ready to make your mark on our roster? Go Guidde!

If you are a backend engineer who sees LLMs as a new architecture building block, enjoys balancing deterministic systems with probabilistic AI, and wants to ship real features - not just experiments - then your place is with us!

What will you do?

You build agents that real customers depend on, and you’re the one who knows, with data, whether they’re getting better. At Guidde, agents answer questions over company knowledge, generate documentation autonomously, and guide users inside the apps they work in. You’ll own how they behave in production.

  • Build agentic products end to end - multi-step agents with tools, retrieval and memory, from design to production (AskAI, g0, agent-facing MCP surfaces)
  • Own quality after launch - golden eval sets, regression gates in CI, production tracing, failure analysis. A release is where measurement starts, not where it ends.
  • Engineer context, not just prompts - retrieval, tool design, structured outputs, guardrails, and human-in-the-loop where it matters
  • Make trade-offs explicit - quality vs. latency vs. cost, model choice vs. retrieval quality, backed by numbers
  • Ship AI-natively - coding agents are your primary dev interface, and you improve the harness that lets them validate their own work

What will you need to have? 

  • 4+ years of production engineering, with strong TypeScript/Node.js
  • At least one LLM or agentic feature shipped to external customers and owned after launch - you can tell us what broke and how you found out
  • Hands-on experience with evals and LLM observability (LangSmith, Langfuse or similar)
  • Solid system design for probabilistic systems: long-running inference, retries, fallbacks, idempotency
  • Product sense - you define what “good” means before you build

Bonus points if you have:

  • LangGraph, MCP or other agent frameworks in production
  • Retrieval at scale (hybrid search, re-ranking)
  • Multi-provider LLM routing, fallback and cost tracking

Your journey with Guidde

  • Leave Your Mark: Build core AI systems that directly shape how thousands of teams create and share knowledge
  • Work Your Way (Hybrid): Enjoy a flexible work arrangement based in Tel Aviv
  • Innovate Together: Collaborate with product, backend, and design teams to turn AI capabilities into real customer value
  • Fuel Your Growth: Expand your skills across AI systems, backend architecture, and product-driven engineering
  • Your Value Matters: Receive a competitive compensation and benefits package

We hire talented and passionate people from a variety of backgrounds because we want our global employee base to represent the wide diversity of our customers. If you're excited about a role but your past experience doesn't align perfectly with every bullet point listed in the job description, we still encourage you to apply. If you're a builder at heart, share our company values, and enthusiastic about making software toolmaking ubiquitous, we want to hear from you.

Demand for AI Engineer roles

New AI Engineer postings at the employers we follow are up 340% over the last 6 weeks compared with the 6 before.

Weekly new AI Engineer postings at the same employers, from the week of August 17 to the week of November 9. The fewest in a week was 78, the most 803, and the latest week had 438.
August 17Last week

Each bar is one week of new postings. The darkest bars are the last 6 weeks.

Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.

About the role

We file this job under AI Engineer, by the work the posting describes.

AI engineers build products on top of AI models that already exist, most often large language models: they connect a model to a company's data and tools and ship the assistants, agents and search features people use.

Postings ask for strong Python or TypeScript, experience with model APIs, retrieval and agent frameworks, and ways to test whether the model's answers are good enough.

An ML engineer trains and serves models; an AI engineer usually starts from a model someone else trained and builds the product around it, though titles often mix the two.

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay

No pay amount identified in the saved description.

Location & working pattern

Tel Aviv, Israel

- LangGraph, MCP or other agent frameworks in production - Retrieval at scale (hybrid search, re-ranking) - Multi-provider LLM routing, fallback and cost tracking
More source context
- Leave Your Mark: Build core AI systems that directly shape how thousands of teams create and share knowledge - Work Your Way (Hybrid): Enjoy a flexible work arrangement based in Tel Aviv - Innovate Together: Collaborate with product, backend, and design teams to turn AI capabilities into real customer value
Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.