AI Engineer – Agentic Applications

Job not on LinkedIn

🔥 45 minutes ago

🇧🇷 Brazil – Remote

⏳ Contract/Temporary

🟡 Mid-level

🟠 Senior

🤖 AI Engineer

👻 Ghost score 10%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Kognit - Committed to Transforming

WebsiteLinkedInAll Job Openings

51 - 200 employees

🤝 B2B

🤖 Artificial Intelligence

Software • B2B • Artificial Intelligence

Kognit is a company specialized in creating unique, tailored, and innovative digital solutions for the corporate market. With 18 years of experience, Kognit helps global companies leverage technology to positively transform their businesses, markets, and the world. The company coordinates and executes projects globally, delivering innovative and scalable software solutions that provide high added value. Kognit is committed to understanding business objectives and providing insights that assist clients in achieving positive transformations in their operations and markets.

📋 Description

• Develop specialist agents coordinated by a supervisor, with agentic loops (ReAct) and auditable decision logging. • Build MCP Servers that connect agents to operational APIs (.NET) and ML models through OpenAPI contracts. • Implement the MCP Host using LangChain / Semantic Kernel and LLMs via Azure OpenAI. • Implement Human-in-the-Loop (HITL) workflows for high-impact decisions. • Ensure agentic security: per-agent identity (OAuth2), tool-level scoping, idempotency, prompt-injection sanitization, and PII leakage prevention. • Version prompts (PromptOps) and instrument agent observability (LangSmith or similar). • Integrate with event-driven architecture (Azure Service Bus / Kafka).

🎯 Requirements

• Bachelor’s degree in Data Science, Computer Science, Statistics, Engineering, Mathematics, Economics, or a related field. • English or Spanish proficiency (international client). • Strong programming skills (Python and/or C#/.NET), including testing, contracts, version control, and readable code. • Experience building LLM applications: tool/function calling, agent orchestration, prompt engineering, and handling nondeterministic behavior. • Systems integration experience: consuming and designing REST APIs (OpenAPI/Swagger), OAuth2 authentication, idempotency, and webhooks/callbacks. • Secure LLM-driven data access—for example, natural language to query with scope control, validation, and auditing. • Familiarity with LLM application security, including prompt injection, data leakage, and tool-level permission controls. • Nice to have: MCP (Model Context Protocol), LangChain or Semantic Kernel, Azure OpenAI, multi-agent patterns, HITL, LangSmith or similar, Kafka/Azure Service Bus, the .NET ecosystem, and experience in regulated environments (LGPD and auditing of automated decisions).

🏖️ Benefits

• Contractor arrangement (PJ); we seek long-term partnerships. • Remote work. • 8-hour workday (168 hours per month). • Time bank reconciled every four months, with positive hours paid out. • Variable compensation after four months of contract. • Flexible benefits card: R$700.00 monthly food allowance on a Flash card. • 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 after 8 years of contract. • Birthday Friday: one day off during your birthday month. • Wellhub partnership. • Open English partnership. • FIAP partnership. • Partnerships with clinics and psychological services.