AI Engineer – Mid-Level

• Design and develop LLM applications, including chatbots, copilots, and autonomous agents
• Integrate and orchestrate model APIs, such as OpenAI, Anthropic, and other providers
• Architect RAG pipelines
• Manage memory, context, and embeddings
• Implement guardrails and response validation
• Optimize latency and token costs
• Configure monitoring and observability for production LLM systems
• Collaborate with technical and analytics teams to identify and resolve bottlenecks
• Lead the development of intelligent and scalable applications
• Ensure reliability, security, and performance in production environments

• Specialization in LLMs
• Backend experience or knowledge with Python or Node.js
• Knowledge of REST APIs
• Knowledge of microservices
• Knowledge of Docker
• Knowledge of cloud platforms: AWS, GCP, or Azure
• Knowledge of LangChain or similar frameworks
• Knowledge of vector databases, such as Chroma and OpenSearch
• Knowledge of AI security, including prompt injection and context control
• Knowledge of logging, tracing, and observability
• Knowledge of CI/CD
• Strong organizational skills and attention to detail
• Scalability-focused mindset
• Systems thinking
• Clear communication with technical and analytics teams
• Proactive identification of bottlenecks
• Commitment to quality and reliability

• Meal and/or food allowance of R$950.00 per month on an iFood card
• SulAmérica health insurance (100% paid by the company)
• Odontoprev dental insurance
• Pet health insurance
• Life insurance
• TotalPass and Wellhub memberships to support physical activities anytime, anywhere
• Birthday day off
• Partnership with Sesc
• Partnership with OnHappy (discounts on hotels and flights)
• Partnerships with educational institutions
• Daycare reimbursement
• Work equipment
• Feedback-driven culture and development opportunities
• Dynamic environment with significant growth opportunities
• Payroll-deducted loan with some of the lowest interest rates
• Variable compensation in recognition of performance, results, and cultural alignment