Forward Deployed Engineer (TypeScript + AI) - Remote - Latin America

FullStack; Manaus; Remote; BRL 180,000 - 300,000; Full time

Benefits offered by this job

Remote work

Continuing education

Grow your career

Work with leading startups

Job summary

FullStack is seeking Forward Deployed Engineers to embed with client teams, turning AI concepts into production systems. You’ll be the consultant, operator and engineer, testing business cases with executives and delivering scoped AI solutions that integrate with client workflows.

You’ll own architecture, design agentic deployments, and drive delivery through CI/CD. The role requires 5+ years of software development, experience with LLM-powered systems, English proficiency, and a track record in

Qualifications

• 5+ years of professional software development experience.
• 1–4 years of experience building and shipping LLM-powered AI systems.
• Advanced English is required.
• Four-year college degree required.
• Experience with APIs, service design, APIs, event-driven and distributed systems.
• Experience owning CI/CD pipelines, including build, test, release, environments.
• Ability to own end-to-end delivery and manage scope without PM supervision.
• Experience in regulated environments or large enterprises is a plus.

Responsibilities

• Discover through workshops to identify AI problems and scoped viewpoints.
• Structure processes and specifications for automation, enabling reliable AI execution.
• Architect and design end-to-end agentic systems, including orchestration and retrieval architecture.
• Build working systems: agents, multi-step automations, internal tooling, integration layers.
• Own CI/CD and delivery environments, ensuring reliable release workflows.
• Consult with CTOs and VPs, articulate decisions, and support pre‑sales scoping.

Skills

Software development

LLM-powered AI

Advanced English

Bachelor’s degree

CI/CD pipelines

APIs & distributed systems

Agile / Scrum

End-to-end delivery

enterprise integration

Discovery calls

Client-facing delivery

Education

Bachelor's degree in a relevant field

Tools

Cursor

Claude Code

Gemini CLI

OpenAI Codex

n8n

MuleSoft

Job description

About FullStack

FullStack is your AI-native engineering partner, built to turn AI capability into certainty. Most companies can demo AI; few can get it to production and prove what it produced. We close that gap with three capabilities, AI built into your products from the start, elite vetted talent who apply it, and transparent execution that shows value every step of the way. With now over 600 customers in North America, FullStack is one integrated partner for all your AI engineering needs. With FullStack, you move forward with confidence.

• Offering life-changing career opportunities to talented software professionals across the Americas.
• Building highly-skilled software development teams for hundreds of the world’s greatest companies.
• Having delivered hundreds of successful custom software solutions, which have positively impacted the lives and careers of millions of users.
• Our 4.1-star rating on GlassDoor.
• Our client Net Promoter Score of 68, twice the industry average.

We’re Most Proud Of

• Offering life-changing career opportunities to talented software professionals across the Americas.
• Building highly-skilled software development teams for hundreds of the world’s greatest companies.
• Having delivered hundreds of successful custom software solutions, which have positively impacted the lives and careers of millions of users.
• Our 4.1-star rating on GlassDoor.
• Our client Net Promoter Score of 68, twice the industry average.

The Position

Forward Deployed Engineers sit inside the client’s problem, not next to it. You embed with an enterprise team, find the work that actually warrants AI, architect the system, build it, and make it hold up in the real environment.

This is a three-way role: consultant, operator, engineer. You should be as comfortable pressure-testing a business case with a COO or VP of Engineering as you are debugging why an agent’s tool-calling loop degraded after a context change. The people who succeed here can hold a discovery conversation on Monday and ship what they scoped on Thursday.

On this track, your edge is application engineering: you make agents real inside the client’s actual systems, workflows, and delivery pipelines.

We work with regulated industries and Fortune 500 clients who have AI mandates, real constraints, and low tolerance for demos that don’t hold up.

How We Approach The Work

FDEs are trusted to shape the solution, not only deliver it. Every engagement calls for architect-level judgment:

• Reframes the request. Treats “we need an agent for X” as a hypothesis, not a spec.
• Decomposes the problem. Outcome → process → decisions → data → systems → actors → constraints — before choosing technology.
• Chooses the intervention. Remove, simplify, traditional software, automation, LLM, RAG, agent, or multi-agent — and defends why.
• Owns the architecture decision. Documents trade-offs (ADRs), sets success metrics, pushes back on scope that won’t deliver value.

Consultative Discovery

Clients rarely arrive with a fully formed problem, and the FDE’s first contribution is helping them see it clearly. You lead discovery with genuine curiosity, moving the conversation from stated requirements to underlying needs, and you build credibility through the depth of your understanding rather than the breadth of your pitch.

• Uncovers business drivers. What outcome matters, what it’s worth, why now, and what happens if nothing changes.
• Uncovers personal drivers. What each stakeholder is measured on, what they’re worried about, and what a win looks like for them individually.
• Surfaces constraints early. Security, compliance, data access, budget, skills, politics, timelines — the things that kill projects in month two.
• Aligns stakeholders. Spots conflicting goals between business, engineering, and risk, and brings them to a shared definition of success.
• Asks strategic questions. Follows the answer with “why,” “how do you know,” and “what happens today when…” — without interrogating. Clients leave the conversation understanding their own problem better.
• Earns authority through depth. Credibility comes from the quality of the questions and the insight in the playback, not from pitching technology.

What You’ll Do

• Discover. Run workshops and process discovery with business and engineering stakeholders. Separate genuine AI problems from workflow problems wearing an AI costume. Come back with a scoped, defensible point of view.
• Structure the process and the spec. For any business or engineering process being automated, map the current state, decision points, and exceptions, then turn it into specifications that both people and AI systems can execute against reliably.
• Architect & design. Design agentic systems end to end — orchestration, context and retrieval architecture, tool and MCP integration, guardrails, human-in-the-loop checkpoints, and the boundaries between deterministic and non-deterministic components.
• Build. Ship working systems — agents, multi-step automations, internal tooling, integration layers. You are hands‑on. Prototypes that prove value in weeks, not slideware.
• Engineer the delivery system. Own CI/CD for what you build: build, test, release, environments.
• Consult. Present to and defend decisions in front of CTOs, VPs of Engineering, and business leadership. Quantify impact in their terms. Support pre‑sales scoping and proposal work when the deal calls for it.

What We’re Looking For

• 5+ years of professional software development experience with at least one mainstream production stack (TypeScript/Node.js, Python, Java, C#/.NET, or Go).
• 1 - 4 years of professional experience building and shipping LLM-powered and agentic AI systems beyond prototypes or demos.
• Advanced English is required.
• Successful completion of a four-year college degree is required.
• Hands‑on experience with frontier AI developer tools including Cursor, Claude Code, Gemini CLI, or OpenAI Codex.
• Proven experience evaluating current‑state environments and defining technical roadmaps.
• Demonstrated experience with APIs, service design, event‑driven and distributed systems, and data modeling.
• Experience designing and owning CI/CD pipelines, including build, test, release, environments, and deployment processes.
• Strong understanding of context and specification engineering to produce reliable AI output.
• Solid understanding of enterprise integration patterns, including APIs, webhooks, event streams, iPaaS platforms such as n8n or MuleSoft, and MCP.
• Track record of leading client‑facing discovery calls, asking “why” before “how” to decompose unstructured business problems.
• Skilled at exercising end‑to‑end delivery ownership and managing project scope without requiring product manager supervision.
• Ability to work through new and difficult issues and contribute to libraries as needed.
• Ability to create and maintain continuous integration and delivery of applications.
• Forensic attention to detail.
• A positive mindset and a can‑do attitude.
• Experience working on Agile / Scrum teams.
• Meaningful experience working on large, complex systems.
• Ability to take extreme ownership over your work. Every day is a challenge to ensure you are performing to the expectations you and your team have agreed upon.
• Ability to identify with the goals of FullStack's clients, and dedicate yourself to delivering on the commitments you and your team make to them.

Strong Plus

• Production AI operations (Day 2): eval harnesses, observability and tracing, cost and token economics, drift, debugging non-deterministic systems.
• Prompt- and eval-level regression testing running in CI and gating releases.
• Delivery in regulated environments (financial services, healthcare, insurance, manufacturing).
• Pre-sales support: discovery calls, SOW and estimate shaping, technical proposal defense.
• Process mining, operations analysis, or transformation consulting background.
• Client enablement and training — building the client team’s capability, not just the system.
• Prior consulting or agency environment; comfort with ambiguity and multiple accounts.

Work Authorization Requirements

• Applicants must be currently authorized to work in the country of this job posting on a full-time basis.
• FullStack will not sponsor applicants for work visas now or in the future.

What We Offer

• Competitive pay.
• 100% remote work.
• The ability to work with leading startups and Fortune 500 companies.
• Continuing education opportunities.
• Opportunity to grow and expand your career.

Our talent network is committed to fostering a diverse, inclusive, and accessible environment where IT professionals can find opportunities that match their skills. We welcome individuals of all races, religions, genders, sexual orientations, national origins, abilities, and experiences. Our focus is on connecting talent with projects based on qualifications, ensuring a fair and transparent process that values diverse perspectives and global collaboration.

Learn more about our Applicants Privacy Notice.