This is a remote position.
- Design and implement robust, scalable, and secure backend services for AI-powered products
- Work closely with data scientists and ML engineers to integrate models into production systems
- Build and optimize APIs, microservices, and data pipelines for real-time and batch processing
- Ensure low-latency inference, efficient model deployment, and resource management
- Maintain and improve CI/CD pipelines, containerization (Docker/Kubernetes), and cloud infrastructure
- Monitor, debug, and optimize backend systems for performance, scalability, and reliability
- Collaborate with cross-functional teams to define system architecture and technical standards
- Stay current with AI infrastructure trends, tools, and best practices
Requirements
- 5+ years of backend software development experience, ideally in Python, Go, or Java
- 2+ years of experience deploying and scaling machine learning models in production
- Solid understanding of RESTful APIs, gRPC, message queues, and microservice architectures
- Experience with ML frameworks (e.g., TensorFlow, PyTorch, ONNX) and serving tools (e.g., TorchServe, Triton, FastAPI)
- Strong knowledge of Docker, Kubernetes, and cloud platforms (AWS, GCP, or Azure)
- Familiarity with data pipelines, distributed systems, and model versioning (MLflow or similar)
- Proficiency in SQL and NoSQL databases (e.g., PostgreSQL, Redis, MongoDB)
- Autorizações de trabalho
- Mundial
- Fusos horários
- Mundial
- Formação
- bachelor degree
- Experiência
- 5+ anos