Software Developer, Payobrain
Payoneer is hiring a Software Developer, Payobrain in Herzliya, Israel. Level rates it ; you can apply on Payoneer.
Level's read on this job
- Works on AI ●●●○ is how Level rates this software engineer role: the daily work is on AI products, without building the model.
- The posting mentions Claude, Cursor and Claude Code among its tools and skills.
- Level classes it as a mid-level role.
- Payoneer has 99 other open roles on Level.
- Posted in the last few days.
AI in this role
About Payoneer
Founded in 2005, Payoneer is the global financial platform that removes friction from doing business across borders, with a mission to connect the world’s underserved businesses to a rising global economy. We’re a community with over 2,500 colleagues all over the world, working to serve customers, and partners in over 190 countries and territories.
By taking the complexity out of the financial workflows–including everything from global payments and compliance to multi-currency and workforce management, to providing working capital and business intelligence–we give businesses the tools they need to work efficiently worldwide and grow with confidence.
Role Summary
As a Software Engineer on the team building Payoneer’s organizational brain, you’ll help create a central, intelligent knowledge layer that connects the company’s many information sources, understands how they relate, and delivers relevant, trustworthy context to both employees and AI agents. At its core is an agent that uses tools such as GraphRAG and Code Graphs to surface relevant context and reliable sources. It’s already widely used across Sales, Legal, Operations, Engineering, Product, and our business units, and it’s the foundation other teams will use to build their own agents and AI solutions.
This is a small team with broad organizational impact. Expect plenty of zero-to-one work, systems thinking, and new technical challenges in information retrieval, semantic search, GraphRAG, Code Graph, agent memory, and agent evaluation. You’ll ship real AI to production, take part in architectural decisions, and shape how Payoneer uses knowledge, builds products, and adopts AI.
Glilot
Hybrid
Full-time
What you'll do
- Design, build, and ship production AI capabilities for Payoneer’s organizational brain, from retrieval pipelines to the agent and tools at its core.
- Develop and improve information retrieval, semantic search, GraphRAG, and Code Graph capabilities that deliver relevant, trustworthy context to employees and AI agents.
- Build the harness before you ship: evaluation frameworks, monitoring, and observability go in on day one, not after the first incident.
- Measure agent quality objectively and systematically: define metrics, build validated test sets, and prove that your changes actually improve results.
- Own your work end to end: understand the business problem, help define and architect the solution, ship it, and monitor it in production.
- Take part in architectural decisions and design reviews, and clearly explain the reasoning and trade-offs behind your design choices.
- Mentor and support others across teams working with different technologies, and non-technical departments as they build on the infrastructure we create.
- Collaborate with Product, engineering teams, and stakeholders across the business to understand their needs and turn them into capabilities, not features.
- Work AI-native, using tools like Claude Code and Cursor to get more leverage and move faster.
Who you are
- Backend engineer with 3-5 years of experience with solid, real-world production experience: you’ve watched systems run in the real world and fixed what breaks.
- Hands-on experience building AI products, especially RAG and agents, and taking them all the way to production, including deployment, evaluation, and ongoing improvement.
- Strong eval instincts: you know how to measure agent quality objectively and systematically, and how to tell whether a change truly improved results, rather than relying on a feeling that the answers look good.
- Experience working in the cloud, especially AWS.
- Team player who enjoys mentoring others, within your team and across teams working with different technologies.
- Strong communicator: you’re comfortable standing in front of people, explaining architectural decisions, and justifying your design choices and the trade-offs behind them.
- Curious and comfortable with ambiguity: you enjoy zero-to-one work, systems thinking, and taking on new technical challenges.
What Could Set You Apart
- Experience with agent memory systems.
- Experience with graphs (such as GraphRAG or knowledge graphs) and knowledge management.
- Experience with our stack: Node.js, TypeScript, OpenSearch (for semantic search), Kubernetes, and MongoDB.
- Fintech or regulated-environment experience: what matters is understanding why “probably fine” isn’t acceptable when money is moving.
- Experience with messaging systems such as Kafka, RabbitMQ, or SQS.
- Experience building SaaS platforms in a cloud-based, microservices environment.
#LI-MP2
The Payoneer Ways of Working
Act as our customer’s partner on the inside
Learning what they need and creating what will help them go further.
Do it. Own it.
Being fearlessly accountable in everything we do.
Continuously improve
Always striving for a higher standard than our last.
Build each other up
Helping each other grow, as professionals and people.
If this sounds like a business, a community, and a mission you want to be part of, apply today.
We are committed to providing a diverse and inclusive workplace. Payoneer is an equal opportunity employer, and all qualified applicants will receive consideration for employment no matter your race, color, ancestry, religion, sex, sexual orientation, gender identity, national origin, age, disability status, protected veteran status, or any other characteristic protected by law. If you require reasonable accommodation at any stage of the hiring process, please speak to the recruiter managing the role for any adjustments. Decisions about requests for reasonable accommodation are made on a case-by-case basis.
How we rate this
Software Developer, Payobrain at Payoneer rates 67 out of 100 for how much of the daily work is AI. That makes it Works on AI (AI Level 3 of 4). The level is about AI in the job, not seniority.
Works on AI. The daily work is on AI products, without building the model.
- ●●●● Builds AI80 to 100
- ●●●○ Works on AI60 to 79
- ●●○○ Uses AI40 to 59
- ●○○○ Little AI0 to 39
Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.
Prepare for this job
Built from this posting and from similar jobs on Level.
Skills and AI tools this role asks for
Pay
- Typical software engineer job
- $167k
This posting doesn't list pay. Use the typical software engineer figure when pay comes up. See software engineer jobs
Questions you could be asked
- How would you design a retrieval step so the model answers from real data instead of guessing?
- How do you decide when an AI agent can act on its own versus asking for approval first?
- What are the limits of Claude that you've run into, and how did you work around them?
- What's a project where you used Cursor hands-on?
- Walk me through how you've used Claude Code in your day-to-day work.
Adapt your resume
- List these exact terms on your resume: RAG, AI agents, Claude, Cursor, and Claude Code. An applicant tracking system matches the wording, not the idea.
- Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
- Show where AI is part of your daily process, not a one-off project. This role expects it to be a running habit.
Get new software engineer jobs (Works on AI ●●●○ or higher) by email
One email a week, each job rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.
Free.
Similar roles
Software Engineering roles that work on AI, at other companies.
What kind of AI work fits you?
Answer 12 practical questions in about three minutes. Get a simple profile, the work it points to, and live roles to explore next.
Find my next step