[Job - 32563] AI Lead Software Engineer, Brazil

ResumeXrays LLC; Brasil; On-site; BRL 420,000 - 540,000; Full time

Benefits offered by this job

Health and dental insurance

Meal and food allowance

Childcare assistance

Extended paternity leave

Wellhub fitness partnerships (Gympass/

Profit Sharing and Results Participat

Life insurance

Continuous learning platform

Well-being discounts

Pregnancy and parenting course

Online learning platform access

Language learning platform

Job summary

CI&T is seeking a technical leader to own the agent SDK and its framework adapters, shaping the public API and versioning strategy while ensuring consistent safety behaviors across Strands, Claude Agent SDK, LangGraph and OpenAI Agents SDK. You will drive architecture for agent loops, MCP servers, and A2A communications, guiding teams through complex multi-agent orchestration patterns.

You will also define extension models, ensure release hygiene, and mentor engineers, splitting large refactors

Qualifications

• Advanced English proficiency (C1+), with international stakeholder communication.
• Extensive years of professional software engineering experience and team leadership.
• Experience building libraries, SDKs or platforms used by others.
• Expert Python (async, typing, packaging, pytest at scale).
• Hands-on production experience building LLM agents with at least one of: Strands Agents, Claude Agent SDK, LangGraph, OpenAI Agents SDK, CrewAI or similar.
• Understanding the agent loop: tool calling, context management, turn limits, streaming; MCP servers/clients and A2A communication.
• Track record of managing breaking changes in widely used internal or open‑source libraries: versioning and migration tooling.
• Strong distributed systems fundamentals: timeouts, retries, idempotency, circuit breakers, backpressure.
• AWS experience, ideally Bedrock and Bedrock AgentCore (Runtime, Gateway, Memory, Identity).
• Clear technical writing: design docs, ADRs, migration guides.

Responsibilities

• Own the SDK as a product: public API, semantic versioning, deprecation policy, migration guides and release hygiene.
• Design and evolve the adapter and host contracts so that agents behave the same across frameworks and deployment targets.
• Lead multi-agent orchestration patterns: supervisor/worker and planner/executor/verifier designs, delegation, A2A protocol support.
• Define the extension model and turn escape-hatches into features.
• Own parity and contract test suite for SDK and templates.
• Lead design reviews and RCAs; turn incidents into platform controls.
• Act as the leader of the team and mentor engineers.
• Split large refactors into parallel tracks and deliver on fixed release dates.

Skills

Advanced English

Software engineering

SDK development

Python

LLM agents

Agent frameworks

Versioning

Distributed systems

AWS Bedrock

Technical writing

Tools

Strands Agents

Claude Agent SDK

LangGraph

OpenAI Agents SDK

CrewAI

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 own the technical direction of the platform's agent SDK (`florence-agentic-ai`) and its framework adapters, the agent and MCP templates, and the runtime contract every agent on the platform depends on.

You decide what the SDK's public API is, how it changes without breaking dozens of teams, and how safety behaviors (loop guards, retry ownership, failure codes, delegation limits) hold the same way across Strands, Claude Agent SDK and LangGraph, over HTTP and A2A.

Responsibilities:

• Own the SDK as a product: public API, semantic versioning, deprecation policy, migration guides and release hygiene (builds you can reproduce, bounded dependencies, publishing from `main` only).
• Design and evolve the adapter and host contracts so that agents behave the same whatever the framework (Strands, Claude Agent SDK, LangGraph) or deployment target (AgentCore Runtime, AgentCore Harness, ECS Fargate).
• Lead multi-agent orchestration patterns: supervisor/worker and planner/executor/verifier designs, declared-peer delegation, A2A protocol support, and ending agent loops by design. Build runtime safety into the SDK: call-chain and hop limits, session cycle budgets, timeouts, per-peer circuit breakers, structured failures that alerts can page on.
• Define the extension model (hooks, per-request settings, escape hatches) and turn repeated escape-hatch use into supported features.
• Own the parity and contract test suite that gates every SDK and template release.
• Lead design reviews and RCAs. Turn incidents into lasting platform controls, not one-off fixes.
• Act as the leader of the teama and also mentor engineers
• Split large refactors into parallel tracks and deliver against fixed release dates.

Requirements:

• Advanced English proficiency (C1 or above), with autonomy to communicate directly with international stakeholders
• Extensive years of professional experiecne with software engineering and leading teams
• Experience building libraries, SDKs or platforms used by other engineering teams.
• Expert Python (async, typing, packaging, dependency management, pytest at scale).
• Hands‑on production experience building LLM agents with at least one of: Strands Agents, Claude Agent SDK, LangGraph, OpenAI Agents SDK, CrewAI or similar.
• You understand the agent loop: tool calling, context management, turn limits, streaming. Experience with Model Context Protocol (MCP) servers and clients, and with agent‑to‑agent communication (A2A or equivalent).
• Track record of managing breaking changes in a widely used internal or open‑source library: versioning, compatibility shims, migration tooling.
• Strong distributed systems fundamentals: timeouts, retries, idempotency, circuit breakers, backpressure, failure propagation.
• AWS experience, ideally Amazon Bedrock and Bedrock AgentCore (Runtime, Gateway, Memory, Identity).
• Clear technical writing: design docs, ADRs, migration guides.

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.

Our 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);
• Discount club-Free online platform dedicated to physical, mental, and overall well‑being
• Pregnancy and responsible parenting course
• Partnerships with online learning platforms
• Language learning platform
• And many more!
• More details about our benefits here: https://ciandt.com/br/pt-br/carreiras

At CI&T, inclusion starts at the first contact. If you are a person with a disability, it is importantto present your assessment during the selection process. See which data needs to be included in the report by clicking here. This way, we can ensure the support and accommodations that you deserve. If you do not yet have the assessment, don't worry: we can support you in obtaining it. We have a dedicated Health and Well‑being team, inclusion specialists, and affinity groups who will be with you at every stage. Count on us to make this journey side by side.