Software Dev Engineer - AI Agents, Ies Latech

Amazon Amazon · Big Tech · SP, Brazil +1 · Software Development

Software Dev Engineer focused on building agentic AI systems for operators in emerging markets, integrating LLMs with internal data and managing trade-offs in latency, cost, and accuracy. The role involves scoping pain points, designing mechanisms, building prototypes, instrumenting metrics, and iterating in production.

What you'd actually do

  1. Review agent runs in production, triage operator corrections, and determine which are bugs versus signal that the autonomy boundary needs to move.
  2. 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.
  3. Close the feedback gap by ensuring every operator correction becomes a test, an eval, or a prompt update, not lost noise.
  4. Own the roadmap end to end. Prioritise, demo weekly, and articulate design choices in writing.
  5. Partner with operations leaders in each market to identify which workflows are agent-ready and which still need a human in the loop.

Skills

Required

  • professional software development
  • architecture and design of new and current systems
  • programming with at least one software programming language

Nice to have

  • full software development life cycle
  • coding standards
  • code reviews
  • source control management
  • build processes
  • testing
  • operations
  • Machine Learning fundamentals
  • Large Language Model fundamentals
  • architecture of LLMs
  • training/inference lifecycles of LLMs
  • optimization of model execution

What the JD emphasized

  • agent capabilities
  • agentic systems
  • agent-ready

Other signals

  • building agent capabilities
  • integrating LLMs with internal data
  • trading off latency, cost, and accuracy
  • monitoring trust score, accuracy, latency, and cost