Senior AI Engineer

Role Summary

We are looking for a top-level AI Engineer to ensure that our Artificial Intelligence solutions not only exist, but operate with maximum production efficiency.

If you have mastery in orchestrating LLMs, RAG architecture and creating autonomous agents integrated into corporate business flows, #VemPraViaflow!

The challenge

You will be the engine behind the development of intelligent applications. Your role is to connect LLMs, APIs and corporate data securely and reliably. If you combine a solid foundation in software engineering with the ability to deliver generative AI solutions ready for enterprise market challenges, this is the place for you.

✨ Did you identify? So come with us!

Develop applications based on LLMs, RAG, agents, copilots and intelligent automations.

Create orchestration flows that connect models, tools, APIs, knowledge bases, and enterprise systems.

Build and optimize context pipelines, embeddings, chunking, information retrieval, reranking and response validation.

Implement guardrails, scope controls, fallback, quality assessment, and hallucination mitigation mechanisms.

Develop APIs and services for consuming the platform's AI capabilities.

Work with prompt engineering, context engineering, tool calling and integration with structured and unstructured data.

Support the definition of quality, cost, latency, security and effectiveness metrics for AI solutions.

Investigate model behavior failures and propose architectural, context or evaluation improvements.

Collaborate with Data, Machine Learning, Platform, Full Stack, Product and Design teams.

Practical experience in developing solutions with generative AI.

Knowledge in LLMs, RAG, embeddings, vector banks, semantic search and context recovery.

Experience with Python and building APIs, preferably with FastAPI or equivalent frameworks.

Familiarity with frameworks such as LangChain, LlamaIndex, CrewAI, Semantic Kernel, LiteLLM or similar.

Good foundation in software engineering, APIs, microservices, relational banks and integrations.

Ability to evaluate quality of responses, diagnose problems and propose technical improvements.

Attention to security, privacy, traceability and responsible use of AI.

Differences

Experience with autonomous agents, multi-agent systems or agentic workflows.

Knowledge in MCP, function calling, tool use and integration of LLMs with external tools.

Experience with pgvector, Pinecone, Weaviate, Qdrant, FAISS or similar mechanisms.

Experience with automated evaluation of LLMs, test datasets, LLM as a judge and AI observability.

Experience with open source models, LLM gateways, model routing and fallback strategies.

Knowledge of LGPD, DLP, data masking, auditing or regulated environments.

Profile we are looking for

We are looking for a curious, technical and objective person. Someone who likes to experiment, but who knows how to separate an interesting demonstration from a ready-to-use solution.

Success indicators

More reliable, testable and reusable AI applications.

Continuous improvement in the quality of responses and reduction of failures.

RAG components, agents and integrations ready for use in different business cases.

Ability to transform customer needs into operable intelligent solutions.

Benefits

• Hiring: Via cooperative model.
• Work Model: Anywhere Office - work from wherever you feel comfortable.
• Technology: BYOD Reimbursement for purchasing a machine and BYOD Assistance for using your own machine.
• Aid: Home office assistance on the iFood card Benefits in the free balance category to use wherever you want.
• Wellbeing: TotalPass, Colab+ Package with access to WellHub, Avus, Starbem and Dasa+ Saúde.
• Additional Benefits: DIT - Temporary Disability Daily, People Hub - Benefits Club, Birthday day off.
• Development: Training and Certifications.