Key skills
AWSCloudDockerGoogle Cloud PlatformMongoDBPythonPyTorchTensorflowAIArtificial IntelligenceMachine LearningMLLangChainLlamaIndexTensorFlowVector DatabasePineconeWeaviateGCPGoogle CloudGitGitHubVersion ControlAtlassianJiraCI/CDRemote Work
About this role
Role Overview
- Design, develop, and ship AI-powered features into BotCity's product, owning the full technical lifecycle from scoping to deployment and monitoring.
- Build production-ready AI components with proper engineering standards: clean code, testing, versioning, observability, and integration into existing infrastructure.
- Establish AI engineering practices for the team — evaluation frameworks, monitoring approaches, deployment patterns — that will scale as the AI footprint grows.
- Collaborate closely with product and engineering to identify where AI creates the most meaningful user value and translate those opportunities into technical proposals.
- Define and monitor technical health metrics for AI components in production, proactively identifying and resolving reliability or quality issues.
- Stay current with relevant AI research and tooling developments and proactively propose how new techniques can be applied to BotCity's product.
- Contribute to code reviews and technical discussions, helping elevate the engineering team's understanding of AI capabilities and limitations.
- Document AI components and decisions clearly to enable knowledge sharing and future maintainability.
Requirements
- Master's degree or equivalent graduate-level education in Computer Science, Artificial Intelligence, Machine Learning, Electrical Engineering, or a closely related field.
- Proven, hands-on command (3+ years) of machine learning and AI engineering concepts.
- Prior experience integrating AI into a commercial software product (not standalone ML models).
- Strong software engineering fundamentals including but not limited to clean code, version control (Git), testing, CI/CD, and the ability to build maintainable, production-ready systems.
- Advanced Python proficiency.
- Hands-on experience with at least one major AI/ML framework or ecosystem (e.g., LangChain, LlamaIndex, HuggingFace, PyTorch, TensorFlow), including familiarity with AI agent frameworks and orchestration patterns, applied in a real project or production context.
- Deep, production-tested experience building Retrieval-Augmented Generation systems.
- Experience building and maintaining Model Context Protocol server infrastructure.
- Experience deploying AI models or components to production — including monitoring, versioning, and infrastructure basics (Docker, cloud platforms such as GCP or AWS).
- Demonstrable project work — GitHub repositories, published models, academic research, or shipped product features — that evidences AI domain mastery independent of years of professional experience.
- Experience with version control system tools such as Git and GitHub, CI/CD.
- Experience with Docker, Docker Compose and building multi-stage container images.
- Experience with at least one Vector Database (e.g. Pinecone, Weaviate, pgvector, MongoDB Atlas Vector, etc).
- Experience working with Atlassian Jira, MS Office/Excel, Google Suite, Notion.
- Ability to travel as needed to support events and meet the team.
- Portuguese
- Fluent.
- English
- Advanced.
Tech Stack
- AWS
- Cloud
- Docker
- Google Cloud Platform
- MongoDB
- Python
- PyTorch
- Tensorflow
Benefits
- Global remote work environment
- Opportunity for professional development and growth