Kastle
Kastle2 open roles

Forward Deployed Engineer

$170–250kSan Francisco, CAOn-siteMidFull-time

Posted 19 days ago

The role in short

Build and deploy production AI agents and full-stack integrations for banking customers, owning the end-to-end lifecycle from prototyping to live monitoring.

About Kastle

Kastle is building the AI employee for banks. We work with some of America's financial institutions, helping them scale their contact center and compliance operations using autonomous AI Agents that process payments, originate loans, and help customers get a world class experience during the biggest financial decisions of their lives. We've processed over $2 billion in transactions and are backed by Insight Partners and Y Combinator. If you are interested in building AI that is applied in the real world where precision, reliability, and performance matter and redefine access to credit across the world, apply below.

We just raised a $24M Series A and are growing fast!

About the Role

As a Forward Deployed Engineer at Kastle, you re-program entire companies.

You are not measured by technical complexity nor lines of code, but by ownership of business outcomes. Agency, judgment, and customer understanding are equally if not more valuable in this role as strong software engineering ability.

You will be driving a fundamental shift in how enterprises operate and how the largest banks in the world operate. You will own our most strategic customers to build and deploy automation and software that was previously impossible. These are not incremental improvements; you'll be replacing load-bearing workflows in production that previously consumed hundreds of thousands of human hours.

This role sits at the intersection of engineering, customer partnership, and operational excellence. You'll go deep into complex enterprise workflows, architect robust Agents using the Kastle Platform.

This role will be the best role for you if you are someone that is excited by business and solving real problems instead of only deriving value from writing code.

Responsibilities

  • Build, configure, and launch AI agents on Kastle’s platform to handle real borrower workflows
  • Write production-grade backend and full-stack code (Python, Java, TypeScript) to integrate with loan servicing systems, data sources, and telephony platforms.
  • Own the full agent development life cycle: prototype quickly, set up CI/CD, monitor live usage, iterate to targets, and document best practices to speed up future projects.
  • Scope ambiguous customer asks, prototype quickly, and iterate into stable deployments.
  • Act as the technical face of Kastle in key accounts, building trust through speed, empathy, and impact.
  • Feed customer learnings back into the core product, influencing roadmap and reusable tooling.

What We’re Looking For

  • At-least 3 years of engineering experience, and 1 year of customer facing experience.
  • Proficiency in Python, Java, or similar; comfortable building APIs and backend systems.
  • Bias toward outcomes: you care more about unblocking customers and delivering value than perfect abstractions.
  • Strong work ethic; very high attention to detail; can own a project end-to-end with limited or no guidance.
  • Customer-centric: confident working directly with business leaders as well as engineers.

Interview Process

  • 15 min interview with our Talent Lead to learn more about the role
  • 1 hour live coding interview with CTO/Founding Engineer
  • 1 hour AI agent design interview with CTO
  • 1 day onsite at HQ

Why join Kastle

  • Opportunity to work with a world class team building a generational AI company that will redefine how every loan in America is made and managed
  • Ability to move fast while your work impacting millions of customers. Add a new feature in a few days and ship it to top 10 lenders the next week.
  • Competitive Compensation + Meaningful Equity at a high growth company
  • High ownership and direct input on product direction, company culture, and how the FDE function scales

Other Perks and Benefits

  • Free MLO training and support
  • Robust medical, vision, & dental coverage
  • 401(K) plan offering
  • Paid Company Meals
  • Company offsites to get to know the team

Prep for this interview

4 questions likely to come up at Kastle, each matched to a line in this posting.

  1. 1Coding
    They wrote: “Write production-grade backend and full-stack code (Python, Java, TypeScript) to integrate with loan servicing systems, data sources, and telephony platforms.”

    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.

    1. Read with a proper CSV parser; check the header first
    2. Validate each row and collect errors, not crash on the first one
    3. Send in batches with retries and a clear report at the end
    4. Write one or two quick tests for the parsing

    Tip: Talk through edge cases out loud: encodings, missing fields, duplicates, rate limits.

  2. 2Integrations and APIs
    They wrote: “Proficiency in Python, Java, or similar; comfortable building APIs and backend systems.”

    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.

    1. Find who owns the system and get read access to a test environment
    2. Watch real traffic or logs to learn the data shapes
    3. Build a thin adapter with logging around every call
    4. 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.

  3. 3LLMs, RAG and agents
    They wrote: “Build, configure, and launch AI agents on Kastle’s platform to handle real borrower workflows”

    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.

    1. Collect and clean the documents; handle permissions per user
    2. Split them into chunks, embed, and store with source links
    3. Retrieve, then answer with citations; say “I don't know” when retrieval is weak
    4. 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.

  4. 4Ownership and working with customers
    They wrote: “Scope ambiguous customer asks, prototype quickly, and iterate into stable deployments.”

    Tell me about a project where the requirements kept changing. What did you do?

    How to answer

    Why they ask: Ambiguity is the norm. They want proof you can keep moving without a clear spec.

    1. The project and why requirements kept moving
    2. What you did to pin them down (short demos, written decisions)
    3. The trade-offs you made to keep shipping
    4. The result, with a number if you have one

    Tip: Show how you reduced the change, beyond how you coped with it.

Not the one? Get the next one by email

New roles land here every day. Pick what you want to hear about.

FDE Info

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.

More at Kastle

Similar roles at other companies

Kastle

$170–250k · On-site

Apply