Own AI-powered healthcare product features end to end, from defining ambiguous problems with clinicians and operators to building, deploying, and monitoring full-stack workflows in production.
AI Engineer Senior, Brazil
š Description
- Develop Python SDK features and adapters for agent frameworks, including memory, skills, prompt management, and evaluation hooks.
- Build and maintain agent and MCP server templates for AgentCore Runtime and ECS Fargate, using HTTP and A2A.
- Integrate with the AWS Agent Registry and build RAG and knowledge services, including ingestion pipelines.
- Write contract and integration tests and maintain the release parity gate.
- Help teams onboard and debug agents, and contribute platform improvements based on what you learn.
- Participate in on-call or office hours and root-cause analyses.
š ļø Requirements
- Advanced English proficiency (C1 or above), with autonomy to communicate directly with international stakeholders
- Extensive years of experience in software engineering, with strong Python: FastAPI or similar, async, packaging, testing.
- 1+ year building LLM-powered applications or agents that reached real users (pilot or production).
- Experience with tool calling, prompt design and handling model failures.
- Familiarity with at least one agent framework (Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, CrewAI, LlamaIndex).
- AWS experience: Lambda, ECS/Fargate, IAM, S3, DynamoDB, and Bedrock or SageMaker.
- Experience with RAG: embeddings, vector stores, chunking and retrieval tuning.
- Comfortable with CI/CD, containers (Docker) and infrastructure-as-code (Terraform preferred). Preferred Bedrock AgentCore (Runtime, Harness, Gateway, Memory, Identity, Code Interpreter). MCP server development.
- A2A protocol. Redis/ElastiCache, OpenSearch. Langfuse or similar LLM observability, prompt management and evaluation tools.
- Experience writing internal developer documentation and samples (notebooks, quick starts).
⨠Benefits
- Health and dental insurance
- Meal and food allowance
- Childcare assistance
- Extended paternity leave
- Partnership with gyms and health and wellness professionals via Wellhub (Gympass) TotalPass;
- Profit Sharing and Results Participation (PLR);
- Life insurance
- Continuous learning platform (CI&T University);
Full job description
At CI&T, we help large enterprises transform the potential of AI into real business impact with AI Deployment, AI-native execution, and tech-integrated business solutions.
With 30 years of experience in technological transformation, we accelerate innovation with expertise in Agentic SDLC, Application modernization, Data & AI, Martech and Business strategy.
We are 8,000 CI&Ters across more than 25 countries, collaborating to build solutions with real impact. AI is already part of how we work, evolve, and innovate every day.
You will build and maintain the core components teams use to ship agents: the Python SDK, agent and MCP templates, memory and context services, the agent registry integration and the FastAPI entry layer. You will often own one component end to end, as primary support.
Responsibilities:
- Build SDK features and framework adapters (Strands, Claude Agent SDK, LangGraph), including memory (AgentCore Memory short- and long-term, Redis), skills, prompt management integration, and evaluation hooks.
- Build and maintain agent and MCP server templates for AgentCore Runtime and ECS Fargate, over HTTP and A2A.
- Integrate with the AWS Agent Registry: registration, approval flow, identity-scoped discovery. Build and support RAG and knowledge services (Bedrock Knowledge Bases, OpenSearch vector, ingestion pipelines).
- Write contract and integration tests.
- Keep the release parity gate green.
- Help use-case teams onboard, debug their agents, and feed what you learn back into the platform.
- Take part in on-call or office hours, and in RCAs.
Requirements:
- Advanced English proficiency (C1 or above), with autonomy to communicate directly with international stakeholders
- Extensive years of experience in software engineering, with strong Python: FastAPI or similar, async, packaging, testing.
- 1+ year building LLM-powered applications or agents that reached real users (pilot or production).
- Experience with tool calling, prompt design and handling model failures.
- Familiarity with at least one agent framework (Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, CrewAI, LlamaIndex).
- AWS experience: Lambda, ECS/Fargate, IAM, S3, DynamoDB, and Bedrock or SageMaker.
- Experience with RAG: embeddings, vector stores, chunking and retrieval tuning.
- Comfortable with CI/CD, containers (Docker) and infrastructure-as-code (Terraform preferred). Preferred Bedrock AgentCore (Runtime, Harness, Gateway, Memory, Identity, Code Interpreter). MCP server development.
- A2A protocol. Redis/ElastiCache, OpenSearch. Langfuse or similar LLM observability, prompt management and evaluation tools.
- Experience writing internal developer documentation and samples (notebooks, quick starts).
Nice to Have:
-
AWS certifications and recent study/project history in agent technology will be accepted in lieu of multiple years of hands-on experience.
Similar jobs
Search more AI Engineer jobsSenior Evaluation AI Engineer
Build and scale evaluation frameworks for multi-agent AI systems, defining quality metrics, safety guardrails, benchmark datasets, and production monitoring to make LLM and RAG workflows reliable.
Design, build, and ship production-ready AI-powered web products end to end, combining full-stack engineering, intuitive interfaces, production LLM features, and reliable infrastructure.
Embed with product teams to identify business problems suited to AI, integrate and extend existing AI services, and build production-ready AI systems with reliable data pipelines, model serving, and monitoring.
Embed with product teams to identify business problems suited to AI, build and integrate production AI capabilities, and shape the services roadmap through hands-on engineering and stakeholder collaboration.
