Skip to content

Wendelmaques: software, speech and AI infrastructure

Over 12 years in software and telecom, with work on speech services, local inference, APIs and system operations. Explore my consulting approach.

By Wendelmaques ·

Experience in engineering and operations

I am Wendelmaques, of WRP Consultoria e Informatica Ltda. I have worked in software and telecom for over 12 years, from C++/Qt and SIP to web services, MySQL, WebRTC and speech systems.

That experience shapes my AI work: a model must operate alongside the application, data, network and the team maintaining the service. I work on architecture, deployment and ongoing operations.

Specialties

  • Local inference with vLLM and GPUs, with explicit memory and concurrency limits.
  • Transcription and speech synthesis, model integration and coordinated GPU use.
  • APIs, queues, data, access control and observability connected to a product.
  • Documented deployment, updates and recovery for the operating team.

Working with your team

Work starts with an assessment of the product, workload and available infrastructure. The proposal defines priorities, responsibilities and acceptance criteria before deployment.

Documentation and knowledge transfer are part of the agreed scope. The aim is for your team to understand system limits and the procedures for operations and recovery.

Engagement options

You can engage me for an infrastructure review, a deployment project or ongoing operations. Scope, pricing and support coverage are defined in the proposal to match your company's needs.

Consulting for your project

Infrastructure review, deployment and ongoing operations, with scope and pricing defined in the proposal.

Consulting

Infrastructure review, deployment and management for your company's AI systems.

Quoted per project