Forward-Deployed AI Engineer

Forward-Deployed AI Engineer

Embed with a US AI startup and own the outcome from fuzzy problem to production agent. Half engineer, half consultant, full owner.

Remote · Latin America · $4,500-$6,000 USD/month · Full-time · Independent Contractor · Monday to Friday · 9 AM-6 PM CT

Why this role exists

Our client is a US AI startup building production AI agents for real customers. They move fast, ship often and turn AI into revenue. They need an engineer who can sit inside their world, run calls with founders and operators in the morning, build and debug in the afternoon, and own outcomes end to end.

What you'll own

• Scoping with the client's operators and execs: sharp questions, fuzzy automation requests turned into concrete, shippable plans, and clear judgment on what not to automate
• Production AI agents with real error handling, retries, idempotency, fallbacks and human-in-the-loop checkpoints across orchestration tools and custom code
• The intelligence layer with LangChain, LangGraph, RAG, structured outputs and voice agents where they fit
• Real-world integrations: REST APIs, webhooks, OAuth2, CRMs, ERPs, Supabase, Airtable and Google Workspace, with write access on live records
• Production reliability: debugging live agents, logging, cost tracking and failure alerts
• The client relationship: explaining tradeoffs to non-technical stakeholders and pushing back on requests that do not make sense
• Reusable templates from each build so the next deployment ships faster

Why this is interesting

• Full ownership from scope to production, not a slice of someone else's spec
• Direct work with founders and operators every week
• A company that turns AI into revenue, not a consulting shop or a lab
• Your rate rises as you take on more scope and complexity

What we're looking for

• 3+ years shipping production software, including real AI and agent work delivered to actual users or clients
• At least one real project shipped end to end: scoped, built and owned when it broke in production
• An army of one: you scope, build, debug and ship without hand-holding, formal specs or a manager pointing the way
• Systems thinking and hands-on experience with production AI against brittle reality: auth failures, flaky data, rate limits
• Strong Python plus at least one of JavaScript or TypeScript
• Fluent with OpenAI and Anthropic APIs, prompt engineering, structured outputs, RAG and evals
• English C1, written and spoken. You run calls with US founders every week

Bonus

• Prior work at an AI-automation agency or as a forward-deployed or solutions engineer
• Vapi or Retell voice agents shipped in production
• Vector databases like pgvector or Pinecone
• Docker and containerization
• Former technical founder or freelancer who carried your own clients

What success looks like

First 90 days

You have completed two full AI agent builds from scope to production, and the client runs them on real workflows. You have a weekly call rhythm with the client team, and you have documented your build process with at least one reusable template for the next deployment.

Ongoing

Your agents run reliably in production with clear observability, cost tracking and sub-hour mean time to resolution on failures. The client sees you as a trusted technical advisor, and you ship new agent builds or significant integrations every 2-3 weeks.

Why Puente

Puente connects experienced Latin American professionals with growing US companies. We do not operate as a generic job board: we selectively match candidates with active roles and guide them through the hiring process.

3% acceptance rate · 2,873+ professionals placed · 97% retention beyond 12 months · 18 countries · 100% remote

Hiring process

• Apply, including a short skills assessment
• Puente screening: a WhatsApp intro, then a recruiter interview
• Client interview with the hiring manager
• Background check and offer

Apply now

Submit your resume in PDF and complete the short skills assessment we share with every applicant. It is how we evaluate written communication, accuracy and attention to detail for this role.