This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Pessoa Engenheira de IA Sênior based in Brazil.
This is a highly technical and hands-on role focused on building and scaling production-grade AI systems powered by large language models.
You will be responsible for designing intelligent applications that go beyond experimentation and operate reliably in real-world enterprise environments.
The role involves working at the intersection of LLM orchestration, RAG architectures, agentic systems, and backend engineering to deliver end-to-end AI solutions.
You will design and optimize data pipelines, context retrieval strategies, and evaluation mechanisms to ensure accuracy, performance, and safety.
A key part of your mission will be transforming business needs into robust AI-powered services integrated with APIs, tools, and corporate data systems.
This is a fast-paced environment where experimentation meets production engineering, requiring strong technical depth and product thinking.
You will collaborate closely with multidisciplinary teams to build scalable, reusable, and high-impact AI components.
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Pessoa Engenheira de IA Sênior based in Brazil.
This is a highly technical and hands-on role focused on building and scaling production-grade AI systems powered by large language models.
You will be responsible for designing intelligent applications that go beyond experimentation and operate reliably in real-world enterprise environments.
The role involves working at the intersection of LLM orchestration, RAG architectures, agentic systems, and backend engineering to deliver end-to-end AI solutions.
You will design and optimize data pipelines, context retrieval strategies, and evaluation mechanisms to ensure accuracy, performance, and safety.
A key part of your mission will be transforming business needs into robust AI-powered services integrated with APIs, tools, and corporate data systems.
This is a fast-paced environment where experimentation meets production engineering, requiring strong technical depth and product thinking.
You will collaborate closely with multidisciplinary teams to build scalable, reusable, and high-impact AI components.
Accountabilities:
- Design, develop, and maintain applications powered by LLMs, RAG pipelines, autonomous agents, copilots, and intelligent automation systems.
- Build orchestration flows connecting models, APIs, tools, vector databases, and enterprise data sources.
- Develop and optimize RAG pipelines, including embeddings, chunking strategies, retrieval, reranking, and response validation.
- Implement guardrails, fallback mechanisms, evaluation frameworks, and hallucination reduction techniques.
- Develop APIs and backend services to expose AI capabilities for internal and external consumption.
- Apply prompt engineering, context engineering, and tool-calling strategies to improve model performance and reliability.
- Define and monitor metrics related to latency, cost, quality, safety, and system effectiveness.
- Investigate model failures and propose architectural or data-driven improvements.
- Collaborate with Data, ML, Platform, Product, and Engineering teams to deliver integrated AI solutions.
- Ensure security, privacy, traceability, and responsible AI usage across all implementations.
- Strong hands-on experience building production solutions with Generative AI and LLM-based systems.
- Deep understanding of LLMs, embeddings, RAG architectures, vector databases, and semantic search.
- Advanced Python skills and experience building APIs, preferably with FastAPI or similar frameworks.
- Experience with AI orchestration frameworks such as LangChain, LlamaIndex, CrewAI, Semantic Kernel, or LiteLLM.
- Solid software engineering background including microservices, APIs, relational databases, and system integration.
- Ability to evaluate model outputs, diagnose issues, and implement technical improvements.
- Strong awareness of AI safety, privacy, security, and responsible development practices.
- Experience with autonomous agents, multi-agent systems, or agentic workflows (differential).
- Familiarity with tool use, function calling, MCP, and external system integrations.
- Experience with vector databases such as pgvector, Pinecone, Weaviate, Qdrant, or FAISS.
- Knowledge of LLM evaluation techniques, observability tools, and testing datasets (differential).
- Experience with open-source models, model routing, and fallback strategies (differential).
- Understanding of LGPD, data masking, auditing, or regulated environments (differential).
- Cooperative contract model with competitive compensation aligned to market standards
- Fully remote (Anywhere Office) work model
- BYOD support for equipment purchase or use of personal machine
- Home office allowance via flexible benefits card
- Wellness benefits including TotalPass, WellHub access, and health platforms
- Additional benefits such as DIT coverage, birthday day off, and discount club access
- Continuous learning opportunities, training, and certifications
- Exposure to cutting-edge AI, hyperautomation, and enterprise-scale solutions
- Collaborative and innovation-driven culture focused on growth and autonomy.