Staff Software Engineer — AI Platform (all genders)
Listed by employer · Checked
Posted within 60 days ·
- Work arrangement
- hybrid
- Employment
- Full-Time
- Stated compensation
- Not specified
- Stated sponsorship
- Not stated
Does the location policy fit?
Choose where you would work from. We’ll compare it with the posting’s stated requirements.
Choose a country to check geographic compatibility. The source requirements are available below.
This checks the posting’s stated requirements, not your legal right to work. Confirm details with the employer.
Requirements
1 with evidence8 unclear or unstated- Remote policy
- hybrid
“Provider workplace type: hybrid”
From employer posting metadata - Employment type
- Full-Time
9 fields not stated in this posting
- Employer sponsorship
- Not specified
- Geographic scope
- Not specified
- Degree requirement
- Not specified
- Security clearance
- Not mentioned
- Timezone / hours
- Not specified
- Citizenship requirement
- Not mentioned
- Minimum experience (years)
- Not specified
- Work authorization
- Not specified
- Compensation
- Not specified
These details were not stated in the tracked posting. Confirm with the employer.
Original job description
Reading view uses normalized posting text so exact evidence excerpts can be highlighted.
Show less description
Original formatting and links
TradeLink builds agentic platforms that lift European supply chains to the next level. Intelligent AI agents take over the routine, while the important decisions and priorities stay with your team. A network connecting companies, suppliers and carriers ensures maximum transparency, reduces lost time, and creates a secure, trusted process. With TradeLink, you're always in command of your logistics — not chasing it.
Build AI that does work — not just talks about it
A supplier changes a delivery date in an email. The new quantity sits in a PDF. The operational system still contains yesterday's information.
TradeLink builds AI agents for real supply-chain operations: agents that understand incoming information, use tools, update workflows and bring humans in when judgment or approval is needed.
The hard part is not getting an LLM to produce a plausible answer. It is building the harness around it so an agent can safely do useful work in a real business.
That is what you will build.
Your responsibilities
As our Staff Software Engineer — AI Platform (all genders), you will build the common runtime behind TradeLink's agentic products.
You will own:
Agent context, tools, state, memory, retries and resumability.
Permissions, tenancy, validation, human approvals and audit trails.
Evals and observability so we can reproduce, measure and debug agent behavior.
Robust patterns for email, documents, APIs, browser-based systems and TradeLink actions.
The line between deterministic application logic and model-driven decisions.
Turning successful customer workflows into reusable platform capabilities.
You will work on questions such as: How does an agent recover when a target system fails halfway through a task? What happens when two messages contradict each other? Which actions can happen autonomously? How do we know an agent change is safe before it reaches production?
This is a hands-on Staff IC role. You will write production code.
What We’re Looking For
We are looking for an experienced software engineer who has gone deep on AI, not someone trying to become an engineer through AI.
Roughly 7+ years of professional software engineering experience, or equivalent depth.
You have owned production systems: architecture, APIs, data models, reliability, observability and incidents.
You have operated at Senior/Staff/Principal level, as a strong Founding Engineer, or with equivalent technical ownership.
You have built LLM or agent workflows that actually run in production — beyond prompts and API calls.
You understand tool calling, structured outputs, state, retries, evals, permissions and human-in-the-loop patterns.
You have strong backend fundamentals: databases, APIs, authentication/authorization, background jobs and failure handling.
Coding agents are already a meaningful part of how you work.
You still enjoy writing substantial production code yourself.
Our core product is built with Ruby on Rails, React, TypeScript and PostgreSQL. Rails experience is useful, but great engineering judgment and learning speed matter more.
Backgrounds that could fit
You might be:
A Staff/Principal Backend or Platform Engineer from a strong SaaS company who became obsessed with agents.
A Founding Engineer from an AI-native startup.
An Applied AI Engineer who is, underneath the title, an excellent software engineer.
A platform engineer from workflow automation, fintech or another environment where software actions have real consequences.
You do not need to be an ML researcher, train foundation models or have a PhD.
This probably isn't for you if
Your AI experience stops at prompting.
You mainly want to research models rather than ship product.
You prefer architecture documents to production code.
You need detailed tickets before making progress.
You want to build a large platform before proving what customers need.
You believe generated code is useful without understanding and verifying it.
How we think about AI
AI should multiply an already strong engineering foundation. We expect you to delegate aggressively to agents — exploration, implementation, testing, debugging — while remaining responsible for the result. You know where agents are excellent. You also know where they confidently produce nonsense.
Verification matters as much as generation.
Why TradeLink
We already sit inside real supply-chain operations. We are not searching for hypothetical AI use cases. Every day, important processes still depend on people reading emails, opening PDFs and Excel files, calling for confirmation and manually transferring information between systems.
We are building an agentic layer around that work.
You get real production problems, direct access to Product and customers, and enough ownership to materially shape how the platform is built.
How we interview
We want the interview to resemble the job. We will talk about systems you have actually built, and in the technical working session AI tools are allowed and expected. We care about how you frame the problem, use AI, make decisions, verify the result and simplify.
One question before you apply: What do you do fundamentally differently as an engineer today because coding agents exist?
What we offer
For more information on data processing in the context of applications, please see our privacy policy for the TradeLink application system.
Matched by role category. Review each posting’s requirements before applying.
