Senior AI Engineer

Casado; Brazil; On-site; BRL 180,000 - 360,000; Full time

Job summary

Casado is seeking a Senior AI Engineer to design and ship customer-facing AI features, including LLM-powered workflows and retrieval systems. You will build production-grade AI agents, APIs, and backends, and ensure reliability in live environments.

The role emphasizes hands-on work with LLM systems, multi-step AI workflows, and strong software engineering across cloud-native stacks, testing, and monitoring to deliver robust AI capabilities for products.

Qualifications

• Experience building and shipping production AI or ML features for customer-facing products.
• Strong hands-on work with LLM systems in production: prompting, RAG, evaluation, guardrails, and cost/latency tradeoffs.
• Experience building multi-step AI workflows or agents with tools, retrieval, and external APIs.
• Strong software engineering skills in Python and production systems built with cloud, Docker, Kubernetes, and CI/CD.
• Solid foundation in ML fundamentals and practical model evaluation.
• Ability to design and implement APIs and backend services that expose AI capabilities to products.
• Strong engineering practices around testing, observability, reliability, and incident debugging.

Responsibilities

• Design and ship LLM-powered product features and AI workflows used by end customers.
• Build and operate retrieval pipelines, tool integrations, and agentic backends.
• Own production quality: testing, monitoring, debugging, and iterative improvement.
• Partner with product and engineering to turn user problems into practical AI implementations.
• Improve reliability, latency, cost efficiency, and observability of AI services.
• Contribute reusable components, patterns, and code quality across the team.
• Support production incidents and participate in on‑call rotations.

Skills

Production AI features

LLM systems in production

Python

Docker

Kubernetes

CI/CD

Observability

On-call readiness

Tools

LangGraph

LangChain

LlamaIndex

Bedrock

SageMaker

Vertex AI

Job description

Own your future:

Our culture isn't something people join, it's something they build and shape. We believe that every person deserves to be heard and empowered. If you're on the fence about whether you're a fit, we say go for it. Let’s build something great together.As a Senior AI Engineer, you will design and ship customer-facing AI features, including LLM-powered workflows, retrieval systems, and production AI agents. This role is for a strong hands‑on engineer who can take ambiguous product problems, turn them into working systems, and operate them reliably in production.

Must-haves:

• Experience building and shipping production AI or ML features for customer-facing products
• Strong hands‑on work with LLM systems in production: prompting, RAG, evaluation, guardrails, and cost/latency tradeoffs
• Experience building multi-step AI workflows or agents with tools, retrieval, and external APIs
• Strong software engineering skills in Python and production systems built with cloud, Docker, Kubernetes, and CI/CD
• Solid foundation in ML fundamentals and practical model evaluation
• Ability to design and implement APIs and backend services that expose AI capabilities to products
• Strong engineering practices around testing, observability, reliability, and incident debugging
• Ability to work independently within a team scope and drive features from design to production

Nice to have:

• Experience with LangGraph, LangChain, LlamaIndex, or similar orchestration tooling
• Experience with vector search, embeddings, reranking, and semantic retrieval
• Experience with Bedrock, SageMaker, Vertex AI, or similar managed AI platforms
• Experience optimizing inference quality, latency, and cost in production
• Experience mentoring other engineers or owning technically complex projects
• Knowledge of distributed systems, data pipelines, and performance tuning

Key responsibilities:

• Design and ship LLM-powered product features and AI workflows used by end customers
• Build and operate retrieval pipelines, tool integrations, and agentic backends
• Own production quality: testing, monitoring, debugging, and iterative improvement
• Partner with product and engineering to turn user problems into practical AI implementations
• Improve reliability, latency, cost efficiency, and observability of AI services
• Contribute reusable components, patterns, and code quality across the team
• Support production incidents and participate in on‑call rotations

Experience building and shipping production AI or ML features for customer-facing products, Strong hands‑on work with LLM systems in production: prompting, RAG, evaluation, guardrails, and cost/latency tradeoffs, Experience building multi-step AI workflows or agents with tools, retrieval, and external APIs, Strong software engineering skills in Python and production systems built with cloud, Docker, Kubernetes, and CI/CD, Solid foundation in ML fundamentals and practical model evaluation, Ability to design and implement APIs and backend services that expose AI capabilities to products, Strong engineering practices around testing, observability, reliability, and incident debugging, Ability to work independently within a team scope and drive features from design to production