Decagon
Decagon6 open roles

Agent Deployment Engineer - Spanish & Portuguese Speaking

Brazil (Remote)RemoteMidFull-time

Posted 2 days ago

The role in short

Design, build, and deploy production-grade AI agents and integrations for enterprise customers, owning the technical delivery from scoping to production.

About Decagon

Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experiences.

Our technology enables industry-defining enterprises like Avis Budget Group, Block’s Cash App and Square, Chime, Oura Health, and Hunter Douglas to deploy AI agents that power personalized, deeply satisfying interactions across voice, chat, email, SMS, and every other channel.

We’re building a future where customer experiences are being redefined from support tickets and hold music to faster resolutions, richer conversations, and deeper relationships. We’re proud to be backed by world-class investors who share that vision, including a16z, Accel, Bain Capital Ventures, Coatue, and Index Ventures, along with many others.

We’re an in-office company, driven by a shared commitment to excellence and velocity. Our values — Just Get It Done, Invent What Customers Want, Winner’s Mindset, and The Polymath Principle — shape how we work and grow as a team.

About the Team

Over the past few years, development of LLMs has evolved at a rapid pace. It’s not enough for our customers to just “set it and forget it” when it comes to AI software. Truly successful AI Agents require hands-on execution, rigorous iteration, and deep technical delivery to reach enterprise-grade performance.

We’re creating an Agent Deployment Engineering Org: a specialized technical delivery team responsible for end-to-end execution of AI agent builds. Agent Deployment Engineers own the hands-on work required to deliver best-in-class agents—writing and configuring key components, validating integrations, and ensuring agents perform reliably at scale. This team brings greater specialization and focus to build quality. Agent Deployment Engineers are technical and customer-facing: you’ll interface with senior technical stakeholders on the customer side while also going deep on agent configuration and build execution.

About the Role

As an Agent Deployment Engineer, you will be responsible for end-to-end execution of AI agent builds for strategic customers. This is a highly technical delivery role where you will own the implementation work required to launch and scale enterprise-quality agents—partnering with customers and internal teams to define success, translate requirements into build plans, and deliver agents that meaningfully impact the customer’s business.

You’ll work closely with Agent PMs, Agent Success, Engineering, and GTM teams to create tight feedback loops: executing builds, surfacing gaps, and influencing the evolution of Decagon’s agent-building platform based on real customer needs. This role is ideal for someone who thrives in fast-moving environments, enjoys shipping customer-facing technical work, and can balance hands-on execution with structured thinking.

In this role, you will

  • Own end-to-end architecture and execution of AI agent builds for enterprise customers, from systems design and initial scoping through implementation, evaluation, and production deployment.
  • Design and engineer the core agentic logic governing agent behavior, applying engineering principles to optimize quality, reliability, and correctness across non-deterministic model outputs.
  • Engineer and validate layered guardrails and supervisory controls to ensure safe, compliant, and predictable agent performance across real-world scenarios.
  • Architect, build, and test integrations with customer systems (e.g., data pipelines, CRMs, ticketing systems), including building the tools, APIs, and workflows needed for reliable deployments at scale.
  • Interface with senior technical stakeholders at customers to define success criteria and system requirements, and drive technical delivery against timelines.
  • Diagnose, debug, and resolve both probabilistic and technical failures through root-cause analysis of execution traces, error logs, and model behavior.
  • Design evaluation and regression-testing frameworks to validate agent behavior against ground truth and guard against performance drift.
  • Translate customer needs into clear internal documentation and run tight feedback loops with Engineering to drive platform improvements.
  • Partner closely with APMs, Engineering, Design, and Go-To-Market teams to deliver consistent, repeatable, best-in-class agent builds.

Your background looks something like this

  • Have 5+ years of relevant experience in a technical customer-facing role (e.g., solutions engineering, forward-deployed engineering, technical consulting, implementation engineering, technical product/PM, or similar).

  • Native or business-level fluency in both written and spoken English, Portuguese and Spanish is required.

  • Strong technical foundation: comfortable writing code, working with APIs, and building/validating integrations end-to-end.

    Experience delivering production-grade customer solutions that require structured execution, testing/validation, and iteration.

  • Ability to communicate clearly with senior technical stakeholders, translate requirements into implementation plans, and drive delivery.

  • Comfort working in fast-moving, ambiguous environments where you shape solutions as much as you implement them.

Even better if you have

  • Experience building with or around LLMs / AI agents (prompting, evaluation, guardrails, tooling, workflow design, etc.).
  • Experience with enterprise SaaS integrations (e.g., ticketing systems, CRM, data pipelines) and associated security/compliance considerations.
  • A Computer Science, Engineering, or Math degree, or equivalent technical experience.
  • Strong product instinct: ability to write crisp PRDs, define success metrics, and contribute customer insight back into product roadmap.

Benefits

We proudly offer the following benefits for our full-time employees:

  • Medical, Dental, and Vision benefits for you and your family
  • Life Insurance and Disability Benefits
  • Retirement Plan (e.g., 401K, pension)
  • Parental Leave
  • Fertility and family building benefits through Carrot
  • Monthly stipend to support your wellness, lifestyle, and work-life balance
  • Daily lunches and snacks in the office to keep you at your best
  • Take what you need vacation policy (subject to local requirements; UK employees receive 25 days of statutory leave)

Decagon offers a competitive benefits package that varies by country and complements local statutory benefits. Details for this location will be provided during the recruitment process.

Prep for this interview

5 questions likely to come up at Decagon, each matched to a line in this posting.

  1. 1LLMs, RAG and agents
    They wrote: “Experience building with or around LLMs / AI agents (prompting, evaluation, guardrails, tooling, workflow design, etc.).”

    How do you know an LLM feature is good enough to ship?

    How to answer

    Why they ask: Evals are what separate a demo from production. Many roles list them by name.

    1. Write 50–200 real examples with expected outcomes, with customer experts
    2. Agree on a pass bar and the errors that are never acceptable
    3. Score automatically where possible; review a sample by hand
    4. Re-run on every prompt or model change, and watch live traffic after launch

    Tip: Describe a test set built with the customer, a pass bar agreed up front, and checks that run on every change.

  2. 2Discovery and scoping
    They wrote: “Interface with senior technical stakeholders at customers to define success criteria and system requirements, and drive technical delivery against timelines.”

    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.

    1. What they asked for, and the detail that made you doubt it
    2. How you tested the doubt (shadowed users, looked at logs, ran a quick prototype)
    3. How you made the case to the customer
    4. What shipped and what changed for them

    Tip: Pick a story where you checked your hunch with data or users before pushing back.

  3. 3Integrations and APIs
    They wrote: “Architect, build, and test integrations with customer systems (e.g., data pipelines, CRMs, ticketing systems), including building the tools, APIs, and workflows needed for reliable deployments at scale.”

    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.

  4. 4Data and SQL
    They wrote: “Experience with enterprise SaaS integrations (e.g., ticketing systems, CRM, data pipelines) and associated security/compliance considerations.”

    How would you design a daily pipeline that feeds customer data into our product?

    How to answer

    Why they ask: Tests basic data engineering: scheduling, failures, re-runs and monitoring.

    1. Extract with timestamps or change tracking, not full dumps, when possible
    2. Transform in steps you can re-run without creating duplicates
    3. Validate row counts and key fields before loading
    4. Alert a person on failure, with enough detail to fix it

    Tip: Make re-running safe (same input, same result) and say how you'd know it failed.

  5. 5Ownership and working with customers
    They wrote: “Comfort working in fast-moving, ambiguous environments where you shape solutions as much as you implement them.”

    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 Decagon

All 5

Similar roles at other companies

Decagon

Remote

Apply