Pessoa Engenheira de Produto de IA Sênior

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Pessoa Engenheira de Produto de IA Sênior based in Brazil.

This is a senior product engineering role focused on turning real operational challenges into practical AI-powered solutions.
You will work end-to-end, from understanding user workflows and identifying automation opportunities to designing, building, and measuring solutions in production.
The role combines backend engineering, generative AI, data architecture, and product thinking, with a strong focus on measurable business impact.
You will make critical decisions about when to use LLMs, RAG, SQL, vector search, automation, or simpler solutions based on the problem at hand.
The environment values ownership, pragmatic technical decisions, rapid experimentation, and continuous iteration based on real user feedback and data.
You will also help establish reliable practices around AI evaluation, observability, security, and LGPD compliance.
The position is fully remote within Brazil, offering the opportunity to influence products and processes while collaborating with multidisciplinary stakeholders.

Accountabilities:

• Discover and analyze operational needs: Conduct shadowing sessions with recruitment, retention, and leadership teams to understand workflows, identify repetitive work, and uncover opportunities for automation and product improvement.
• Prioritize opportunities by impact: Evaluate operational problems based on expected business value, technical feasibility, and clearly defined success metrics, prioritizing solutions that effectively reduce operational time and user friction.
• Design end-to-end architectures: Define solutions spanning data sources such as APIs, spreadsheets, and emails, while determining appropriate approaches for LLMs, data storage, observability, security, and LGPD compliance.
• Make deliberate technical trade-offs: Select the right models and architecture for each problem, including decisions around LLM selection, RAG versus traditional SQL, synchronous versus asynchronous pipelines, and relational versus vector databases.
• Build full-stack AI solutions: Develop solutions across the required layers, from backend services, LLM integrations, data pipelines, and databases to web interfaces, bots, or intentionally interface-free workflows.
• Build for reliability and security: Implement robust error handling, retry logic, circuit breakers, access controls, and data anonymization before sensitive information is sent to external AI models.
• Measure and improve impact: Monitor adoption, operational time savings, model error rates, latency, and other relevant metrics; create Evals to assess hallucination and model reliability in production and continuously iterate based on user feedback and observability data.
• Document and share knowledge: Record architectural decisions, version prompts as code, document solutions, and facilitate knowledge transfer so that successful approaches can be maintained and evolved by the wider engineering team.

Requirements

• Professional experience: Proven experience as a Backend Developer, including designing and implementing complex APIs and systems that integrate multiple data sources, as well as hands-on experience integrating LLMs into real-world applications beyond tutorials or proof-of-concepts.
• Backend architecture and APIs: Strong knowledge of complex API orchestration and distributed systems, with practical experience implementing resilience patterns such as retry logic, circuit breakers, and robust error handling.
• Generative AI: Hands-on experience applying LLMs through approaches such as RAG, function calling, structured parsing with Pydantic or JSON Schema, and prompt versioning, while considering latency, cost, and reliability.
• Hybrid data modeling: Experience working with both relational and vector databases and the ability to make sound decisions about when to use traditional SQL queries versus semantic similarity search.
• AI reliability and observability: Experience designing evaluation frameworks to monitor hallucinations, accuracy, and model quality in production, together with strong observability practices.
• Security and LGPD: Ability to design secure data pipelines, including anonymization of sensitive information, access controls, and privacy-conscious integration with external AI services.
• Adaptable software development: Strong software engineering fundamentals and the ability to work across backend services, asynchronous pipelines, bots, and web interfaces depending on what best solves the user's problem.
• Valued technical experience: Production experience with vector databases such as Pgvector, Pinecone, or Qdrant; real-world RAG pipelines; corporate integrations involving HCM or ERP systems and protocols such as SAML, OIDC, or SCIM; and development tools such as Cursor, GitHub Copilot, or Claude Code.
• Product and business mindset: Ability to prioritize solutions that deliver tangible operational value rather than unnecessary technical sophistication, understand workflows before coding, and focus on solving the specific user problem before generalizing.
• Ownership and communication: Comfortable working with ambiguity, collaborating with non-technical stakeholders, questioning disproportionate or technically unviable proposals, documenting decisions, explaining trade-offs, and owning solutions from problem discovery through impact validation.
• Pragmatic execution: Able to rapidly implement solutions to validate hypotheses while recognizing when refactoring or deeper architectural investment is appropriate, with a strong sense of judgment around technology selection and data sensitivity.
• Continuous learning: Proactive about understanding business context, evolving technical knowledge, experimenting with new approaches, and taking responsibility for outcomes across the full solution lifecycle.

Benefits

• Flexible benefits card: Access to a multi-benefit card covering categories such as meals, food, mobility, health, home office, culture, and education.
• Healthcare: Health insurance with no copayment, with available provider options including Unimed, SulAmérica, or Alice.
• Mental health support: Access to online therapy and coaching sessions through Zenklub.
• Wellness: Wellhub membership and access to online medical consultations through Conexa Saúde.
• Learning and development: Language-learning support through Rosetta Stone and access to Alura for professional development.
• Time off: Dedicated recharge day off to support rest and well-being.
• Family support: Childcare assistance.
• Remote work: 100% remote work, allowing you to work from anywhere within Brazil.
• Work equipment: Company-provided equipment to support your remote setup.
• Career growth: Opportunities to grow professionally while contributing to an evolving technology environment and taking meaningful ownership of products and solutions.

How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best!  Why Apply Through Jobgether?    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.     #LI-CL1