Engenheiro(a) de IA - Aplicações Agênticas (Pleno)

Lever, Inc.; Brasil; Teletrabalho; BRL 180 000 - 280 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

PJ contractor model

Fully remote work

8-hour workday (168 hours/month)

Bank of hours with quarterly settling

R$700/month food allowance

Birthday month day off

Resumo da oferta

Lever, Inc. seeks an Engenheiro(a) de IA - Aplicações Agênticas (Pleno) in Brazil to design and build advanced AI-powered apps using GenAI, LLMs, and agentic systems. You will craft specialized AI agents, orchestrate workflows, and ensure secure, auditable decisions across cloud services.

You will work with LangChain, Semantic Kernel, and Azure OpenAI, focusing on reliability, observability, and human oversight for critical choices in an international client context.

Qualificações

• Experience building LLM-powered apps with tool/function calling.
• Strong REST API and OpenAPI experience, plus OAuth2.
• Knowledge of agentic patterns and human-in-the-loop workflows.

Responsabilidades

• Develop AI agents coordinated by supervisors and maintain auditable records.
• Build MCP Servers connecting agents with APIs and ML models.
• Implement MCP Hosts using LangChain or Semantic Kernel and integrate Azure OpenAI.
• Design Human-in-the-Loop workflows for high-stakes decisions.
• Ensure secure agent architectures with identity, permissions, and anti-prompt-injection safeguards.
• Apply PromptOps with versioned prompts and observability (LangSmith).
• Integrate AI apps with event-driven architectures using Azure Service Bus and Kafka.

Conhecimentos

Python

C#/.NET

Testing

Version control

OpenAPI/Swagger

OAuth2

REST API

LLM tooling

Agent orchestration

Prompt engineering

Security for LLMs

Formação académica

Bachelor’s or postgraduate in Data Science/CS/Engineering/Math

Ferramentas

LangChain

Semantic Kernel

Azure OpenAI

Kafka

Azure Service Bus

MCP

Descrição da oferta de emprego

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Engenheiro(a) de IA - Aplicações Agênticas (Pleno) based in Brazil.

This role is an opportunity to build advanced AI-powered applications using Generative AI, LLMs, and agentic systems. You will design and develop specialized AI agents capable of coordinating complex workflows and making traceable decisions. The position combines software engineering, AI orchestration, system integration, and application security. You will work with technologies such as MCP, LangChain, Semantic Kernel, and Azure OpenAI. The role also involves event-driven architectures, observability, and human oversight for high-impact decisions. It is an ideal environment for professionals who want to turn emerging AI technologies into scalable, secure, and high-impact solutions.

Accountabilities

• Develop specialized AI agents coordinated by supervisors, implementing agentic loops such as ReAct and maintaining auditable records of decisions and actions.
• Build MCP Servers that connect AI agents with operational APIs and machine learning models through well-defined OpenAPI contracts.
• Implement MCP Hosts using frameworks such as LangChain or Semantic Kernel and integrate LLM capabilities through Azure OpenAI.
• Design and implement Human-in-the-Loop workflows for decisions that require human validation, oversight, or intervention.
• Establish secure agentic architectures, including agent-specific identities, OAuth2 authentication, tool-level permissions, idempotency, prompt-injection protection, and safeguards against PII leakage.
• Apply PromptOps practices by versioning prompts and implementing agent observability through LangSmith or similar platforms.
• Integrate AI applications with event-driven architectures using technologies such as Azure Service Bus and Kafka, while ensuring reliable communication between services.

Requirements

• Bachelor’s or postgraduate education in Data Science, Computer Science, Statistics, Engineering, Mathematics, Economics, or a related field.
• Professional proficiency in English or Spanish, with the ability to communicate effectively in an international client environment.
• Strong programming skills in Python and/or C#/.NET, including experience with testing, version control, software contracts, and writing maintainable, readable code.
• Hands-on experience developing LLM-powered applications, including tool or function calling, agent orchestration, prompt engineering, and strategies for managing non-deterministic model behavior.
• Solid understanding of system integration and REST API development or consumption, including OpenAPI/Swagger, OAuth2 authentication, idempotency, webhooks, and callbacks.
• Experience enabling secure LLM access to data, including natural-language-to-query workflows with appropriate scope controls, validation, permissions, and auditability.
• Understanding of application security for LLM-based systems, including prompt injection, data leakage, and permission management at the tool level.
• Experience with MCP, LangChain or Semantic Kernel, Azure OpenAI, multi-agent architectures, Human-in-the-Loop patterns, agent observability, Kafka, Azure Service Bus, or .NET is considered a strong advantage.
• Familiarity with regulated environments, LGPD requirements, and auditing of automated decisions is also valuable, along with a proactive, analytical, collaborative mindset and a strong interest in emerging AI technologies.

Benefits

• PJ contractor model with a focus on building long-term professional partnerships.
• Fully remote work.
• 8-hour workday, totaling 168 hours per month.
• Bank of hours with quarterly settlement and payment of positive balances.
• Variable compensation after four months of contract.
• Flexible benefits card with R$700 per month for food allowance through Flash.
• Paid time off: 7 consecutive days after 1 year of contract, 15 days after 2 years, 21 days between 5 and 7 years, and 30 days from 8 years onward.
• Birthday month day off through the “Sexta Presente” benefit.
• Wellhub partnership.
• Open English partnership.
• FIAP partnership for professional development.
• Partnerships with clinics and psychology services.
• Opportunities to work with innovative AI technologies and challenging digital solutions in an international environment.

We appreciate your interest and wish you the best!

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.