We are not hiring right now. What has been open stays here.
No open roles today, and no process under way. When one opens, it opens on this page. Below are the three roles Moonxi has advertised, with the whole description — enough to see the technical level we look for without having to ask.
Open roles
We are not taking applications for any position. If you want to be on the radar for the next one, send a CV and a link to some code to contato@moonxi.com.br. We answer when a front opens that fits — no open process, no maintenance conversation.
Roles that have been open.
All closed. They stay published because the description says more about the work than any institutional paragraph — and because deleting what was already advertised is the kind of thing we do not do. Click to open the full description. These were published in Portuguese; what you read here is a translation of that text.
AI/ML Engineer Mid/Senior
Build and grow Moonxi's AI systems: agents with tool orchestration, multi-model integration and RAG, in the in-house product and in client projects.
We are looking for a mid/senior AI Engineer to work on site in São Paulo, leading the construction and evolution of our artificial intelligence systems.
Our in-house product is an AI-first platform with more than 40 AI tools, autonomous agents, multi-model integration (GPT, Claude, Gemini and Chinese models) and orchestration that connects tasks, code and cloud infrastructure. We also apply AI in our clients’ projects, from conversational agents for customer support to document-processing pipelines and decision systems.
What you would do
- Architect and build AI agents with tool orchestration, conversational context and multi-step reasoning
- Integrate and orchestrate several language models (OpenAI, Anthropic, Google) with fallback strategies, rate limiting and cost optimization
- Implement RAG (retrieval-augmented generation) systems with embeddings, semantic search and knowledge bases
- Build tool calling and integrations between AI agents and external systems (GitHub, AWS, WhatsApp, CRMs, financial APIs)
- Design prompts and system instructions that produce consistent, reliable results in production
- Build processing pipelines with Python and FastAPI, with performance and scalability in mind
- Define quality metrics for AI output and implement evaluation and feedback mechanisms
- Work with the product and engineering team on AI architecture decisions
Requirements
- Solid experience with Python (FastAPI, Pydantic or similar frameworks)
- Hands-on experience with LLM APIs (OpenAI, Anthropic/Claude, Google Gemini) in production
- Advanced prompt engineering, and techniques such as few-shot, chain-of-thought, MCP and skills
- Experience building AI agents with tool orchestration and short- and long-term memory
- Familiarity with RAG: embeddings, vector stores, chunking strategies, semantic search
- Relational databases (PostgreSQL) and/or non-relational ones (MongoDB, Redis)
- Experience with REST APIs and systems integration
- The ability to weigh trade-offs between models, cost, latency and output quality
Nice to have
- Experience with agent frameworks (PydanticAI, LangChain, CrewAI, AutoGen or similar)
- AWS services (Lambda, EC2, S3, SQS, Bedrock)
- Experience with Node.js/TypeScript as well as Python
- Familiarity with Docker and deploying services to the cloud
- Experience with audio and speech processing (Whisper, transcription)
- Fine-tuning and model adaptation techniques
- Experience with AI observability (call tracing, cost monitoring, quality evaluation)
- Technical English for reading papers and documentation
What we offer
- Work directly on the AI core of a product we own
- Autonomy to propose and test approaches with frontier models (GPT, Claude, Gemini)
- A mix of work: the in-house product plus applied AI for clients in healthcare, finance and construction
- A technical environment where architecture decisions are made by the people building it
- Real room to grow in a company that is scaling
- Direct contact with what is new in AI
Stack named in the advert
The publication date and the closing date were never recorded, so they are not on the page. What exists is the advert, transcribed above as it was published.
Full Stack Developer Mid/Senior
React/Next.js on the front end and Node.js/TypeScript on the back end, in an AI platform-engineering product — mobile, web and desktop.
We are looking for a mid/senior Full Stack Developer to work on site in São Paulo. The focus is an AI platform-engineering product, across mobile, web and desktop.
What you would do
- Build front-end interfaces with React/Next.js and back-end services with Node.js/TypeScript
- Design and implement scalable APIs with third-party integrations (WhatsApp, CRMs, financial services)
- Work with AWS infrastructure (Lambda, EC2, S3, RDS, SQS) and deploy containerized applications
- Take part in architecture decisions with the team
- Keep quality up through code reviews, tests and the technical documentation that matters
Requirements
- Solid experience with Node.js and TypeScript (back end and/or full stack)
- React.js and/or Next.js
- Experience with AWS services in production (Lambda, EC2, S3, RDS, SQS or similar)
- Familiarity with relational databases (PostgreSQL, MySQL) and non-relational ones (MongoDB, DynamoDB)
- REST APIs
- Experience with Docker and containerized environments
- Clear communication, and the ability to work in a multidisciplinary team
Nice to have
- Python (FastAPI, automations, scripts)
- Experience with projects involving AI and LLMs (OpenAI, Claude, RAG, embeddings)
- Familiarity with CI/CD and automated deployment pipelines
- Experience with event-driven architectures and messaging (SQS, Kafka, RabbitMQ)
- Experience with monitoring and observability tools (CloudWatch, Datadog, Grafana)
- Technical English
What we offer
- Technically varied projects — our own AI product plus clients in different sectors
- An environment with no bureaucracy, where your technical opinion counts
- Direct contact with architecture and product decisions
- Real room to grow in a company that is scaling
- Work with current technology (generative AI, intelligent agents, cloud-native)
Stack named in the advert
The publication date and the closing date were never recorded, so they are not on the page. What exists is the advert, transcribed above as it was published.
Backend Developer Mid
Back-end APIs and services in Node.js/TypeScript, microservice architecture and third-party integrations — Open Finance, WhatsApp and CRMs.
We are looking for a mid-level Backend Developer to join our development team. You will work on demanding projects involving complex integrations, microservice architecture, AI and cloud infrastructure.
What you would do
- Build and maintain scalable back-end APIs and services
- Design and implement solutions using microservice architecture
- Work with third-party integrations (Open Finance, WhatsApp, CRMs)
- Work with the team on technical and architecture decisions
- Keep code quality up through tests and good practice
- Take an active part in code reviews and technical documentation
Requirements
- Solid experience with Node.js and TypeScript
- Python
- Experience with AWS services (Lambda, EC2, S3, RDS, SQS, among others)
- Familiarity with relational and non-relational databases
- REST and/or GraphQL APIs
Nice to have
- Experience with containerization
- CI/CD
- Experience with event-driven architectures
- Familiarity with monitoring and observability tools
- Experience with projects involving AI and LLMs
What we offer
- A collaborative environment with no bureaucracy
- Varied and technically demanding projects
- Room to grow and to keep learning
Stack named in the advert
The publication date and the closing date were never recorded, so they are not on the page. What exists is the advert, transcribed above as it was published.
When a role opens, it opens here.
Until then, this page stays as it is. If you want to work with us, send a CV and a link to some code — that is what we read first.
Send a CV →