Full Stack AI Developer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Full Stack AI Developer based in Brazil.

This role offers the opportunity to build next-generation AI systems that combine real-time data, structured knowledge, and autonomous intelligence. You will contribute across the full technology stack, from high-performance data pipelines and knowledge graphs to AI agent orchestration and interactive user experiences. You will design reliable agentic systems capable of reasoning, using tools, querying complex knowledge sources, and producing grounded results. The role combines modern Python backend engineering with GenAI, data engineering, cloud infrastructure, and frontend development. You will work closely with technical and domain experts to translate complex real-world challenges into scalable software solutions. A strong focus on performance, traceability, testing, and reliability will be essential as these systems operate in demanding real-world environments. This is an ideal opportunity for a versatile engineer who enjoys solving complex problems and moving comfortably across the stack.

• Design, build, and deploy advanced agentic AI systems using frameworks such as LangGraph and LangChain, enabling stateful agents to plan tasks, query knowledge sources, and execute tools reliably.
• Develop Graph-RAG pipelines that combine semantic search with structured knowledge traversal to deliver accurate, contextual, and grounded responses.
• Build AI agents capable of integrating with engineering tools, simulators, databases, APIs, and other enterprise knowledge sources.
• Collaborate with domain experts to ensure agent behavior aligns with technical requirements, business objectives, and real-world constraints.
• Implement safeguards, evaluation mechanisms, and traceability features that improve the accuracy, reliability, and explainability of AI-generated outputs.
• Continuously optimize prompts, agent orchestration, system performance, and model interactions for production environments.
• Develop low-latency Python services and REST APIs using FastAPI to provide real-time data to AI models and frontend applications.
• Build scalable data and ingestion workflows capable of handling high-volume streams and complex data processing requirements.
• Contribute to knowledge graph solutions and ontology modeling for representing complex relationships across physical assets and technical data.
• Develop interactive React-based AI assistants, including chat interfaces, canvas experiences, dashboards, and data visualization components.
• Work across backend services, AI orchestration, data platforms, and frontend applications while making informed architectural and technical trade-offs.
• Apply sound software engineering practices, including testing, documentation, API design, maintainability, and performance optimization.
• Investigate system behavior through logs, monitoring, and data analysis to identify root causes of failures, data anomalies, performance issues, and disconnected graph relationships.
• Contribute to cloud-native deployments and infrastructure across Kubernetes and hybrid-cloud environments.
• Deliver solutions rapidly while maintaining high standards for code quality, reliability, testing, and scalability.

Requirements

• 5+ years of professional experience in Python backend development, with strong expertise in modern Python, asynchronous programming, typing, and performance-conscious software development.
• 2+ years of experience with modern frontend frameworks such as React and/or Angular, together with strong TypeScript skills.
• Practical experience building applications powered by large language models, agentic AI frameworks such as LangGraph, and vector databases.
• Strong experience designing, developing, and documenting REST APIs, particularly using FastAPI.
• Solid understanding of computer science fundamentals, including data structures, algorithms, Big O notation, and CPU/memory optimization.
• Strong full-stack mindset with the ability to work across backend services, AI orchestration, data pipelines, and frontend interfaces.
• Advanced English communication skills, with the ability to collaborate effectively with technical and domain stakeholders.
• Familiarity with GenAI technologies such as LangGraph, LangChain, LiteLLM, Azure OpenAI, Anthropic, local small language models, and MCP (Model Context Protocol).
• Experience with technologies such as Kafka, Neo4j, Apache Airflow, Trino, Apache Iceberg, MinIO, Delta Lake, Polars, Spark, Kubernetes, Terraform, or hybrid-cloud platforms is valuable.
• Experience building evaluation pipelines for agentic AI systems using tools such as LangSmith, Ragas, or custom evaluation frameworks is a strong advantage.
• Knowledge of streaming technologies such as Kafka, Flink, or Spark and time-series databases such as TimescaleDB or InfluxDB is beneficial.
• Hands-on experience with graph databases such as Neo4j/Cypher, SQL database design, and hybrid search strategies is preferred.
• Experience working with heavy industry, oil and gas, IoT, or industrial data environments, including technologies such as MQTT or OPC UA, is a plus.
• Familiarity with local LLM deployments such as Ollama and privacy-focused AI architectures is advantageous.
• Knowledge of data lineage or metadata management is a plus.
• Strong analytical and problem-solving abilities, with a proactive approach to investigating technical issues and identifying root causes.
• Ability to work collaboratively, manage priorities, communicate technical decisions clearly, and operate effectively in a fast-moving engineering environment.

Benefits

• Fully remote position based in Brazil.
• Full-time employment with the opportunity to work on advanced AI and software engineering initiatives.
• Competitive compensation commensurate with experience and level.
• Opportunity to work across GenAI, autonomous agents, knowledge graphs, real-time data, cloud infrastructure, and full-stack development.
• Exposure to modern technologies including LangGraph, FastAPI, React, Kafka, Neo4j, Kubernetes, Terraform, and hybrid-cloud architectures.
• Opportunity to solve complex technical challenges involving real-time data, structured knowledge, and autonomous intelligence.
• Collaborative environment with opportunities to work alongside technical specialists and domain experts.
• Opportunity to contribute to high-impact AI systems designed for demanding real-world applications.
• Professional growth opportunities across engineering, AI, data, cloud, and full-stack technologies.
• Flexible remote working environment designed to support distributed collaboration.

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Why Apply Through Jobgether?

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1