AI Engineer

Crew; Ciudad de México; Hybrid; MXN 1,800,000 - 2,400,000; Full time

Job summary

Jeeves is seeking a senior AI Engineer to own end-to-end AI workflows, designing agentic systems and building production-grade LLM pipelines. You will work closely with Product and Backend Engineering, shipping AI-powered features with minimal handholding.

You will apply your expertise to design, implement, and monitor multi-step AI workflows, ensuring reliability, cost efficiency, and regulatory compliance while collaborating with customers and cross-functional teams.

Qualifications

• 7+ years of professional software engineering experience.
• Ownership of a large system or workflow end to end, from scoping and design through launch and iteration.
• Hands-on experience shipping LLM-powered applications with APIs such as Anthropic, OpenAI, or similar.
• Experience designing agentic or multi-step AI workflows (tool use, orchestration, human review steps).
• Strong proficiency in Python, plus REST APIs, PostgreSQL or similar relational databases, async patterns, and a major cloud provider (AWS, GCP, or Azure).
• Experience with observability for AI systems: logging, tracing, dashboards, and quality monitoring.
• Professional fluency in English, written and spoken.

Responsibilities

• Design agentic and LLM-based systems that combine extraction, retrieval, reasoning, and tool use to complete multi-step work, with clear human-in-the-loop points.
• Write design docs, make build-vs-buy and model choices, and set success metrics for each workflow you own.
• Build production-grade LLM pipelines: prompt design, context design, structured outputs, validation, fallbacks, and confidence scoring.
• Integrate AI services with Jeeves's backend: clear API contracts, retries, graceful degradation, and per-customer data isolation.
• Manage cost and latency across models, choosing the right model for each step.
• Build evaluation sets and automated evals for every workflow you own to catch regressions.
• Instrument AI components with logging, tracing, dashboards, and alerts to detect quality drops.
• Keep an audit trail of AI decisions that meets regulatory standards.

Skills

7+ years software engineering

End-to-end ownership

LLM-powered apps

Agentic/multi-step AI workflows

Python

REST APIs

PostgreSQL

Async patterns

Cloud provider

Observability

English fluency

Tools

OpenAI API

Anthropic API

LLM pipelines tooling

Job description

Jeeves is the stablecoin-native banking platform for global enterprises. Thousands of companies across 35 countries run their corporate cards, payments, treasury and spend on one platform, with more than $5B in annualized volume, payouts to 190 countries, and one of the fastest-growing stablecoin payment networks in the world. BMW, H&M, Lululemon, Burger King, Kavak and XP are among them, and more than 80% of customers use multiple Jeeves products.

We chose hard problems on purpose.

We hire for one thing: relentlessness. A strong motor that keeps going when the problem has no playbook. You'll know in your first week if Jeeves is right for you. For the right people, it's the steepest learning curve of your career.

Jeeves has raised more than $400 million in equity funding from Andreessen Horowitz, Y Combinator, CRV, Coinbase Ventures, GIC, AllianceBernstein, CoinFund and others.

If you want to rebuild how money moves across borders, come build it with us.

As an AI Engineer at Jeeves, you will own whole workflows from end to end, not individual features. You'll decide how to build it, ship it, measure it, and keep improving it. You'll work closely with Product, Backend Engineering, and our customers, but you won't wait for someone to hand you a spec.

This is a senior, hands‑on role for people who are AI‑native in how they work. You use coding agents and AI tools every day to move faster, and you know where they fall short. It isn't a research role, and it isn't a role for someone who wants a narrow, well‑defined ticket queue.

Location: This role is remote or hybrid based out of Mexico City, Mexico, and is a full‑time remote position where it is also possible to come into our office in Roma Norte on a flexible schedule. #LI-REMOTE

What You'll Do:

Own AI Workflows End to End

• Design agentic and LLM‑based systems that combine extraction, retrieval, reasoning, and tool use to complete multi‑step work, with clear human‑in‑the‑loop points
• Write the design docs, make the build‑vs‑buy and model choices, and set the success metrics for each workflow you own

Build Reliable AI in Production

• Build production‑grade LLM pipelines: prompt and context design, structured outputs, validation, fallbacks, and confidence scoring
• Integrate AI services cleanly with Jeeves's backend: clear API contracts, retries, graceful degradation, and per‑customer data isolation
• Manage cost and latency across models, choosing the right model for each step

Measure, Monitor, and Improve

• Build evaluation sets and automated evals for every workflow you own, and use them to catch regressions when prompts, models, or data change
• Instrument AI components with logging, tracing, dashboards, and alerts so you know when quality drops before a customer does
• Keep an audit trail of AI decisions that meets the standards of a regulated financial product

Raise the Bar for AI Engineering at Jeeves

• Set patterns, shared tooling, and practices that other engineers can build on
• Show the wider team how to use coding agents and AI tools well in day‑to‑day engineering
• Review peers' AI system designs and share what you learn openly

Minimum Requirements:

• 7+ years of professional software engineering experience, including at least 2 years building and operating LLM or AI‑powered systems in production
• A track record of owning a large system or workflow end to end, from scoping and design through launch and iteration, with limited direction
• Hands‑on experience shipping LLM‑powered applications with APIs such as Anthropic, OpenAI, or similar, including structured outputs, error handling, and evaluation
• Experience designing agentic or multi‑step AI workflows (tool use, orchestration, human review steps)
• Strong proficiency in Python, plus solid backend fundamentals: REST APIs, PostgreSQL or similar relational databases, async patterns, and a major cloud provider (AWS, GCP, or Azure)
• Experience with observability for AI systems: logging, tracing, dashboards, and quality monitoring
• Professional fluency in English, written and spoken