AI Engineer Applied AI · São Paulo or Remote (Americas) · Applied AI

Amber.ai; São Paulo; Remote; BRL 120,000 - 180,000; Full time

Benefits offered by this job

Equity

Health/dental/vision coverage

25 days PTO

Learning budget

Home office stipend

Job summary

Amber is building the next generation of augmented AI for operational data. We design, implement, and deploy retrieval and orchestration layers that connect products, orders, suppliers, and freight data to support real-time decision-making.

You will contribute to evaluation harnesses that keep outputs precise as the product evolves, and ship end-to-end workflows with the product engineering team. This is a software-first role with emphasis on practical impact.

Qualifications

• Three or more years of production software engineering, with recent LLM application work.
• Hands-on experience with retrieval pipelines, structured outputs, and evaluation tooling.
• Strong Python or TypeScript engineering fundamentals: this is a software role first.
• Judgment about when AI is the right tool and when a form field is.

Responsibilities

• Design retrieval and orchestration pipelines over products, orders, suppliers, and freight data.
• Build evaluation harnesses that keep assistant answers precise as the product evolves.
• Ship assistant-driven workflows into production modules with the product engineering team.
• Tune latency, cost, and quality trade-offs across model providers.
• Prototype fast, measure honestly, and kill what does not work.

Skills

LLM application work

Retrieval pipelines

Python

TypeScript

Evaluation tooling

Software design

Tools

Git

Docker

CI/CD

Job description

You will build the assistant layer of AmberOS (retrieval, orchestration, and evaluation over live operational data) so a brand can ask a question and act on the answer in the same breath.

• Design retrieval and orchestration pipelines over products, orders, suppliers, and freight data.


• Build evaluation harnesses that keep assistant answers precise as the product evolves.


• Ship assistant-driven workflows into production modules with the product engineering team.


• Tune latency, cost, and quality trade-offs across model providers.


• Prototype fast, measure honestly, and kill what does not work.

What we look for

• Three or more years of production software engineering, with recent LLM application work.


• Hands-on experience with retrieval pipelines, structured outputs, and evaluation tooling.


• Strong Python or TypeScript engineering fundamentals: this is a software role first.


• Judgment about when AI is the right tool and when a form field is.


• Bias for shipping measurable improvements over polishing demos.

Nice to have

• Experience with agentic workflows acting on ERP-like systems.


• Published evals, open-source tools, or writing about applied LLM work.


• Familiarity with supply chain or commerce data.


• Competitive salary and meaningful equity


• Health, dental, and vision coverage


• 25 days of paid time off


• Annual learning and conference budget


• Home office setup stipend