Software Engineer, Agent Delivery
Posted Sep 18, 2026
The role in short
Deploy production AI agents and workflows inside supply chain companies by embedding with customers to design integrations, debug systems, and ship solutions.
About Pallet
Pallet is building AI Agents to transform the physical economy, a $12 trillion global TAM. We’ve raised $50M from top investors, including General Catalyst, Bessemer Venture Partners, and Bain Capital Ventures.
Our mission is to increase the efficiency of the global supply chain by automating the manual workflows that slow supply chain teams down. Our flagship platform provides end-to-end visibility, and control.
As companies across the physical economy look to drive efficiency, many are turning to Pallet to lead the way. With deep supply chain expertise and cutting-edge AI capabilities, we’re positioned to build the next $10B company powering the physical economy.
Join us and work alongside leaders from Google, DoorDash, YC, and more to shape the future of supply chain technology.
About The Role
We’re hiring a Software Engineer, Agent Delivery to deploy production AI agents inside some of the world’s largest supply chain companies.
You’ll work directly with customer operators, engineers, and executives to understand how critical workflows actually run. Then you’ll design integrations, debug production systems, and ship AI-powered workflows into environments that are often undocumented, fragmented, and business-critical.
This role sits at the intersection of engineering, product, and customer operations. You’ll own deployments from initial discovery through production launch, spending time with customers both remotely and onsite, solving complex operational problems and turning those solutions into reusable product capabilities.
Success in this role is measured by outcomes: can you get systems live, make them reliable, and solve problems in environments you don’t fully control? Every deployment teaches us something new about how supply chain companies operate. The patterns you uncover become product features, and what you solve for one customer often becomes a capability we ship across the platform.
The impact you will have
- Lead high-impact customer deployments from problem definition through production, designing, prototyping, building, and deploying AI agents and workflows that change how work gets done and run reliably at scale.
- Embed in customer workflows and build relationships from ICs and operators up to executives, turning messy business requirements into clear technical solutions that solve the underlying problem, not just the first request.
- Make design decisions across agent behavior, application logic, data, evals, security, and reliability, and set the patterns for how Pallet agents are deployed in production.
- Connect Pallet agents to the systems, APIs, and data customers already rely on, working directly with their engineering and ops teams to get around technical constraints.
- Stay accountable after launch by debugging failures, evaluating and improving agent quality, and working with Engineering and Product to clear anything blocking a successful deployment.
- Turn what you learn in the field into reusable agents, integrations, evals, and frameworks, and bring recurring needs and product gaps back to Product and Engineering to shape the core platform.
Who You Are
- 3+ years of experience building and owning production systems in high-growth startups or similarly demanding environments.
- Strong experience working with APIs, integrations, authentication systems, and event-driven architectures.
- Proven ability to debug complex systems in production.
- Comfortable operating in ambiguous environments where documentation is incomplete, and requirements evolve quickly.
- Strong communication skills and the ability to build trust with technical and non-technical stakeholders.
- Experience working directly with customers is a strong plus
Our Tech Stack
- Backend: Node + TypeScript on Encore.dev. Event-driven design with message passing and queues. Hosted on GCP
- Database: PostgreSQL
- LLMs: OpenAI, Anthropic, Google for foundation models; fine-tuned models on Vertex AI
- Browser Automation: Playwright
- Frontend: Next.js + React + TypeScript. Hosted on Vercel
- Observability: Datadog for logging and metrics
Location: San Francisco, Fidi 5 days a week
The estimated salary range for this role is $145,000–$245,000, depending on experience and skill set. In addition to base salary, we offer competitive equity, benefits, and growth opportunities. Final compensation will be determined based on a combination of factors, including experience, qualifications, and location.
Our Benefits
We invest in our people the same way we invest in our product: seriously.
- 🩺 Health, Vision, and Dental benefits
- 🏝️ Take-what-you-need Paid Vacation
- ➕ Life Insurance and Accidental Insurance
- ❤️🩹 Short-Term Disability Coverage
- 💸 Generous salary and equity for all staff
- 🪜 401k option; helping you save for the future
- 🧑🧑🧒🧒 Paid parental leave to support growing families
- 📚 Yearly learning and development stipend
- 🚌 Commuter benefits for Bay Area and New York employees
- 🚘 Uber ride stipend if you ever have to work late in the office
- 🏡 Remote office home stipend to get you comfy in your space for remote employees
- 📸 Free professional headshot
- 🍔 Daily catered lunches and dinners provided in office
- 💪 Complimentary On-Site Gym: Our SF office has a fully equipped gym
- ✈️ Onboarding trip to one of our offices if you work remotely
- 🥤 Monthly happy hours
- 🎉 Annual Company Offsites; our last one was in Palm Springs CA 🌴
Workplace Policy
We are an in-person company. Our offices in San Francisco, New York City and London are where ideas get built, decisions get made, and the team gets stronger. We have invested in making them genuinely great places to spend your day, with catered lunches, monthly happy hours, and people who care about the work and each other.
Most of our team works in office five days a week. For select roles, we hire remotely across the U.S. Remote employees come to one of our offices for their first week to onboard and meet the team, and we cover the full trip.
Every role is different. Travel expectations are always shared upfront in the job description and confirmed in your first call with us.
Equal Opportunity
Pallet is an Equal Opportunity Employer. We make all employment decisions based solely on merit. We provide equal employment opportunities to all applicants and employees without discrimination on the basis of race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, disability status, or any other applicable legally protected characteristic. We prohibit any form of discrimination or harassment. This policy applies to all terms and conditions of employment, including hiring.
Candidate Privacy Notice
Please review Pallet’s Candidate Privacy Notice here.
Accommodations
Pallet complies with the Americans with Disabilities Act (ADA), as amended by the ADA Amendments Act, and all applicable state or local laws. We will reasonably accommodate qualified individuals with a disability during the application process and throughout employment as required by law.
If you need any assistance or accommodations due to a disability, please contact us at recruiting@pallet.com.
Prep for this interview
5 questions likely to come up at Pallet, each matched to a line in this posting.
- 1Integrations and APIs
They wrote: “Strong experience working with APIs, integrations, authentication systems, and event-driven architectures.”
Walk me through connecting our product to a customer's internal system that has no documentation.
How to answer
Why they ask: This happens weekly in the job. They want a calm, step-by-step method.
- Find who owns the system and get read access to a test environment
- Watch real traffic or logs to learn the data shapes
- Build a thin adapter with logging around every call
- Agree on how failures get reported, and who fixes what
Tip: Talk about finding the owner of the system first. The code is the easy part.
- 2LLMs, RAG and agents
They wrote: “LLMs: OpenAI, Anthropic, Google for foundation models; fine-tuned models on Vertex AI”
A customer wants a chatbot over their internal documents. How do you build it?
How to answer
Why they ask: RAG is the most common first project. They want the whole path, from messy files to answers people trust.
- Collect and clean the documents; handle permissions per user
- Split them into chunks, embed, and store with source links
- Retrieve, then answer with citations; say “I don't know” when retrieval is weak
- Build a test set of real questions with expected answers before launch
Tip: Spend more time on the data and on testing than on the model.
- 3Discovery and scoping
They wrote: “Comfortable operating in ambiguous environments where documentation is incomplete, and requirements evolve quickly.”
Tell me about a time the customer asked for one thing but needed another.
How to answer
Why they ask: Good FDEs spot when a request is a guess at a solution. They want proof you can redirect a customer without losing their trust.
- What they asked for, and the detail that made you doubt it
- How you tested the doubt (shadowed users, looked at logs, ran a quick prototype)
- How you made the case to the customer
- What shipped and what changed for them
Tip: Pick a story where you checked your hunch with data or users before pushing back.
- 4Cloud, deployment and security
They wrote: “Make design decisions across agent behavior, application logic, data, evals, security, and reliability, and set the patterns for how Pallet agents are deployed in production.”
The customer's security team sends a 200-question review. How do you handle it?
How to answer
Why they ask: Security reviews often block deals. FDEs help get through them.
- Start from your company's standard answers (SOC 2 report, past reviews)
- Answer clearly; don't oversell
- Bring in your security team for anything you're unsure of
- Keep the new answers for the next customer
Tip: Reuse past answers, flag honest gaps, and offer a call for the hard questions.
- 5Coding
They wrote: “Backend: Node + TypeScript on Encore.dev. Event-driven design with message passing and queues. Hosted on GCP”
Here's a CSV export from a customer. Write a script that cleans it and loads it into our API.
How to answer
Why they ask: Very close to real FDE work. They watch how you handle bad rows and failures.
- Read with a proper CSV parser; check the header first
- Validate each row and collect errors, not crash on the first one
- Send in batches with retries and a clear report at the end
- Write one or two quick tests for the parsing
Tip: Talk through edge cases out loud: encodings, missing fields, duplicates, rate limits.
Not the one? Get the next one by email
New roles land here every day. Pick what you want to hear about.
Want the job, not just the posting? Learn how FDEs work.
FDE Info is our free weekly newsletter for forward deployed engineers: tools, field notes from real deployments, and how FDE teams hire and pay.
Free. One email a week. Unsubscribe in one click.
