Job Description
Important Information
Location: Brazil
Job Mode: Full-time
Work Mode: Work from home
Job Summary
As an AI Specialist, you will be the technical lead for the intelligence layer of this MVP. Your role is to design and optimize the Agentic Architecture using Azure AI Foundry, ensuring that the supervisor and sub-agents perform complex reasoning over engineering data. You will be responsible for the “brain” of the application, focusing on prompt engineering, RAG strategy (Retrieval-Augmented Generation), and ensuring the solution is explainable and compliant. You will work in a highly collaborative duo with a Fullstack AI Engineer to deliver a sophisticated AI solution within a 3-month timeframe.
Responsibilities and Duties
- Design and implement the Supervisor Agent logic and goal-driven specifications;
- Develop and refine system prompts for specialized agents (Completion, Depth Calculation, etc.);
- Lead the RAG strategy, defining indexing patterns, chunking strategies, and hybrid search configurations in Azure AI Search;
- Evaluate and optimize model performance (Foundry Models) focusing on accuracy and “explainability” for engineering outputs;
- Conduct experimentation and testing to mitigate hallucinations and ensure Petrobras/Halliburton compliance;
- Participate in technical discussions and demonstrations, explaining the AI’s reasoning and logic to stakeholders;
- Oversee AI Observability, including tracing, evaluation, and cost management within the Azure ecosystem.
Essential Skills
- Solid Experience with LLMs: Deep understanding of GPT-4/Turbo/o1 models and their limitations;
- Agentic Frameworks: Proven experience with LangChain, AutoGen, or CrewAI;
- RAG Expertise: Solid experience with Vector Databases and semantic search (specifically Azure AI Search);
- Prompt Engineering: Advanced skills in designing complex, multi-step prompt chains and system instructions;
- Python Mastery: Solid experience with Python focused on Data Science and AI;
- Evaluation Frameworks: Experience using tools to evaluate LLM outputs (faithfulness, relevancy, etc.).
Highly Desirable Skills
- Knowledge of Azure AI Foundry (Prompt Flow, Content Safety);
- Experience with specialized data extraction from complex technical documents (Word/PDF);
- Background in Engineering, Math, or Data Science;
- Understanding of Fine-tuning vs. RAG trade-offs;
- Familiarity with “Human-in-the-loop” design patterns for AI validation.
About Encora
Encora is the preferred digital engineering and modernization partner of some of the world’s leading enterprises and digital native companies. With over 9,000 experts in 47+ offices and innovation labs worldwide, Encora’s technology practices include Product Engineering & Development, Cloud Services, Quality Engineering, DevSecOps, Data & Analytics, Digital Experience, Cybersecurity, and AI & LLM Engineering.
At Encora, we hire professionals based solely on their skills and qualifications, and do not discriminate based on age, disability, religion, gender, sexual orientation, socioeconomic status, or nationality.
