Want to know if this job is worth applying to?
Brasil
Hybrid
At CI&T, we help large enterprises transform the potential of AI into real business impact with AI Deployment, AI-native execution, and tech-integrated business solutions.
With 30 years of experience in technological transformation, we accelerate innovation with expertise in Agentic SDLC, Application modernization, Data & AI, Martech and Business strategy.
We are 8,000 CI&Ters across more than 25 countries, collaborating to build solutions with real impact. AI is already part of how we work, evolve, and innovate every day.
We’re looking for a Soda FDE to make sure the data behind our AI agents can be trusted. You’ll need experience with Soda, including defining and automating data quality checks, monitoring pipelines and catching anomalies, gaps and schema changes before they reach production. We expect you to be able to turn business rules into measurable quality standards and build data governance into the solution’s architecture. You should be comfortable working closely with clients to understand what reliable data means for them. Above all, you’ll be a full-stack engineer who sees data quality as a business outcome and can deliver working agents built on validated, reliable data.
Requirements
7–10+ years of practical experience in delivering fullstack applications
1. Software Engineering Fundamentals and Integration
Build robust end-to-end solutions and connect them to existing infrastructures.
Programming Languages: Deep proficiency in Python (the gold standard for AI and data) and TypeScript/JavaScript (essential for web applications and APIs).
API Development and Consumption: Absolute mastery of RESTful and GraphQL architectures to integrate the core product into the client's legacy systems.
Databases: Solid knowledge of both traditional relational databases (SQL) and non-relational databases (NoSQL) to extract data from wherever it lives.
2. Artificial Intelligence and Data Ecosystems (The core differentiator)
AI-assisted development: daily use of Cursor, GitHub Copilot, or Claude Code; disciplined about reviewing, testing, and refactoring agent-generated code to team standards.
LLM product basics: hands-on with LLM APIs (OpenAI, Anthropic, Azure OpenAI, or equivalent); practical understanding of prompting, RAG-style Q&A, streaming UX, and common failure modes (hallucination, latency, cost).
3. Infrastructure, Cloud, and DevOps
Deploy code seamlessly into the client's cloud environment (Azure).
Engineering standards: comfort applying tests, code review, CI/CD, and security practices during iterative delivery, not only at the end of a project.
Data Science / Data Engineering: Core tools for handling pipelines and cleaning large data volumes (minimum requirements are Databrics and SODA).
4. Communication
Professional English in a technical environment is mandatory (written and spoken) for specifications, reviews, risk communication, and day-to-day collaboration.
Good communication to align task status, understanding of requirements and escalate any hurdles or blockers that impact the work to be done
#LI-BM2
