Full Stack Engineer/Medical Technology

ADP is hiring a Senior Full Stack Developer – Assist AI Platform

Are you excited about building conversational and agentic AI experiences that will support millions of users?

Are you a backend-leaning engineer who loves shaping resilient serverless architectures and intelligent orchestration layers?

Do you want to drive large-scale AI systems that are already in production—not prototypes—while still keeping a hand in pragmatic UI integration?

Well, this may be the role for you. Ready to help evolve a production-grade enterprise AI platform?

Hybrid work model in the office located in Porto Alegre/RS.

About the Role

You will join the ADP Assist AI Platform team delivering next‐generation conversational assistants and intelligent automation. Our AI and agent orchestration stack is live in production, serving real enterprise workflows and scaling to millions of interactions. You'll architect and build serverless services, low-latency GraphQL & event APIs, and AI agent orchestration capabilities that connect to Bedrock, OpenAI, Anthropic, and internal action agents. You'll shape multi-environment reliability, performance, security, and operational excellence across a large ecosystem of shared services, packages, and deployable units. Frontend work is a supporting slice—not the center—ensuring rich conversational experiences surface the intelligence your services provide.

What You'll Do

• AI / Agent Orchestration: Create execution flows, tool/function calling, conversation state & memory models, and provider abstraction layers.
• Backend & APIs: Implement NestJS serverless (Lambda + API Gateway) services, scalable GraphQL schemas/resolvers, and focused REST endpoints.
• Data & Event Flows: Use event-driven patterns (pub/sub, async triggers) for orchestration, streaming responses, and action agent pipelines.
• Quality Engineering: Enforce TDD; expand Jest suites (unit, integration, contract) for Lambdas & GraphQL.
• Performance Optimization: Profile hot paths (invocation latency, cold starts, resolver timing), optimize caching & streaming strategies.
• Frontend Integration (Supportive): Enable conversational UI consumption via lightweight Stencil.js components & GraphQL patterns—keep abstractions clean.
• Documentation & Architecture: Follow ADRs, sequence diagrams, API specs, and operational runbooks.
• Continuous Improvement: Refine coding standards, automate quality gates (ESLint, SonarQube), and evolve build/test acceleration for a large codebase.

Key Responsibilities

• Architect and evolve AI agents & orchestration pipelines.
• Build and operate production NestJS Lambda services with Handlers & REST interfaces.
• Integrate LLM providers (AWS Bedrock, OpenAI, Anthropic) through unified capability interfaces (completion, tools, embeddings, moderation).
• Implement conversation state handling and instrumentation for traceability.
• Support integration of conversational UI components while keeping backend contracts stable & versioned.
• Maintain high automated test coverage and contract integrity (consumer/provider tests).

Required Qualifications

• Experience: 8+ years professional full stack development with clear depth in backend architecture & distributed systems.
• Backend Core: NestJS (primary), Node.js, Express.js, GraphQL, REST API design, MongoDB operations.
• AI / LLM Integration: Hands-on with OpenAI/Anthropic and/or AWS Bedrock.
• Serverless & Cloud: Deployment of AWS Lambda, and event-driven patterns.
• Frontend (Supportive): Working knowledge of TypeScript, Web Components, and integrating framework-agnostic UI components.
• Architecture: Designing modular services and scalable API surface areas for a large multi-team codebase.
• Education: Bachelor's degree in Computer Science / Engineering or equivalent experience.

Preferred Qualifications

• Conversational AI design patterns (dialog state machines, memory strategies, streaming UX semantics).
• Agent orchestration (multi-model routing, tool chaining, fallback & retry semantics, guardrail enforcement).
• Real-time delivery (WebSockets, SSE, event streams) and token streaming optimization.
• Internationalization (i18n) & accessibility (WCAG) considerations.
• Performance tuning (cold start mitigation, bundle trimming, resolver latency, concurrency shaping).

To Succeed In This Role

• Ownership: You treat services, pipelines, and quality gates as products you steward end-to-end.
• Deep Systems Thinking: Model latency, failure modes, and scaling characteristics before coding.
• Collaboration: Communicate clearly with AI/ML scientists, security, product, and UX partners.
• Curiosity: Track rapidly evolving LLM features and responsibly integrate them.

You'll Love Working Here Because You Can

• Build AI workflows.
• Deliver at scale with measurable reliability goals.
• Continuously learn in a fast-moving AI + serverless ecosystem.
• Contribute to social responsibility and inclusive culture initiatives.
• Join a company committed to equality, equity, and inclusive growth.

A Little About ADP

ADP provides global cloud human capital management solutions—spanning payroll, talent, time, tax, and benefits—underpinned by large‐scale data, analytics, and compliance expertise. Innovation, client impact, and inclusive collaboration are core to how teams build and iterate.

Diversity, Equity & Equal Employment Opportunity

*O modelo de trabalho adotado pela ADP é office based/presencial, com a possibilidade de trabalho em home-office por até duas vezes na semana.

"Considerando que as atividades desempenhadas pelos ocupantes deste cargo envolvem acesso a informações altamente confidenciais e sensíveis de clientes da ADP e de seus respectivos empregados, a ADP reserva-se o direito de conduzir checagem de histórico, de tempos em tempos, conforme autoriza o Incidente de Recurso de Revista Repetitivo no 01 do Tribunal Superior do Trabalho, mediante consentimento do candidato/trabalhador"

What are you waiting for? Apply today