Back to jobs
Product Engineer - AI Agents, IES LATech & GIS
Sao Paulo, Sao Paulo, BRAPosted Yesterday
Full-timeonsite
Job Description
Amazon is hiring a Product Engineer to focus on Agentic AI in Australia, building the capabilities that let AI agents act reliably on real operator workflows. You'll join a specialist team of Product Engineers, Scientists, and Developers within Amazon's emerging-markets technology organisation, focused on sustainable growth across Latin America and Australia.
Your customers are operators. Planners, ops managers, analysts, support leads. They make hundreds of small judgement calls a day, and your job is to give them agent capabilities that absorb the repetitive ones so they can focus on the calls that actually matter.
In this role you are part builder, part product owner. You scope the pain, design the mechanism, build the prototype, instrument the metrics, then iterate in production. You build the primitives, integrations, and mechanisms behind agentic systems, integrating large language models with internal data and trading off latency, cost, and accuracy with judgement, not by recipe.
Key job responsibilities
- Review agent runs in production, triage operator corrections, and determine which are bugs versus signal that the autonomy boundary needs to move.
- Pair with operators on workflows you are scoping. Watch them work, ask why behind every step, and translate implicit rules into mechanisms the agent can execute.
- Close the feedback gap by ensuring every operator correction becomes a test, an eval, or a prompt update, not lost noise.
- Own the roadmap end to end. Prioritise, demo weekly, and articulate design choices in writing.
- Partner with operations leaders in each market to identify which workflows are agent-ready and which still need a human in the loop.
- Translate ambiguous operator pain points into concrete, measurable mechanisms with clear success criteria.
- Monitor trust score, accuracy, latency, and cost per decision. Dig into regressions before they compound.
Amazon is hiring a Product Engineer to focus on Agentic AI in Australia, building the capabilities that let AI agents act reliably on real operator workflows. You'll join a specialist team of Product Engineers,
- Experience developing operational processes and technologies
- Working knowledge of LLM-based applications: prompting, tool/function calling, evaluations, and the trade-offs between latency, cost, and accuracy.
- Experience integrating with internal or external APIs, data sources, and services.
- Experience building AI agents or agentic systems in production.
- Familiarity with composable agent primitives: tool use, memory, retrieval, evaluation harnesses, and model-swap patterns.
- Track record of working backwards from operator or customer workflows.
- Experience defining metrics for trust, accuracy, or autonomy and using them to gate rollout.
- Experience operating in ambiguity; taking a vague business problem and converging it into a shipped mechanism.
Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.
Your customers are operators. Planners, ops managers, analysts, support leads. They make hundreds of small judgement calls a day, and your job is to give them agent capabilities that absorb the repetitive ones so they can focus on the calls that actually matter.
In this role you are part builder, part product owner. You scope the pain, design the mechanism, build the prototype, instrument the metrics, then iterate in production. You build the primitives, integrations, and mechanisms behind agentic systems, integrating large language models with internal data and trading off latency, cost, and accuracy with judgement, not by recipe.
Key job responsibilities
- Review agent runs in production, triage operator corrections, and determine which are bugs versus signal that the autonomy boundary needs to move.
- Pair with operators on workflows you are scoping. Watch them work, ask why behind every step, and translate implicit rules into mechanisms the agent can execute.
- Close the feedback gap by ensuring every operator correction becomes a test, an eval, or a prompt update, not lost noise.
- Own the roadmap end to end. Prioritise, demo weekly, and articulate design choices in writing.
- Partner with operations leaders in each market to identify which workflows are agent-ready and which still need a human in the loop.
- Translate ambiguous operator pain points into concrete, measurable mechanisms with clear success criteria.
- Monitor trust score, accuracy, latency, and cost per decision. Dig into regressions before they compound.
Amazon is hiring a Product Engineer to focus on Agentic AI in Australia, building the capabilities that let AI agents act reliably on real operator workflows. You'll join a specialist team of Product Engineers,
- Experience developing operational processes and technologies
- Working knowledge of LLM-based applications: prompting, tool/function calling, evaluations, and the trade-offs between latency, cost, and accuracy.
- Experience integrating with internal or external APIs, data sources, and services.
- Experience building AI agents or agentic systems in production.
- Familiarity with composable agent primitives: tool use, memory, retrieval, evaluation harnesses, and model-swap patterns.
- Track record of working backwards from operator or customer workflows.
- Experience defining metrics for trust, accuracy, or autonomy and using them to gate rollout.
- Experience operating in ambiguity; taking a vague business problem and converging it into a shipped mechanism.
Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.