Senior AI Systems Engineer (Edge & Inference) in Brazil, Indiana at Jobgether

This position is posted by Jobgether on behalf of a partner company. We are currently looking for a Senior AI Systems Engineer (Edge & Inference) in Brazil.

This role is focused on bringing advanced AI models into high-performance production environments, with a strong emphasis on efficiency, scalability, and ultra-low latency. You will work at the intersection of machine learning engineering and systems engineering, transforming cutting-edge LLMs, multimodal, NLP, and computer vision models into robust, production-ready services. The position involves close interaction with specialized hardware and optimized inference stacks to ensure maximum computational efficiency. You will be responsible for building and tuning inference pipelines that operate at scale in enterprise and edge environments. This is a highly technical role suited for someone who thrives in performance-critical systems. You will collaborate with multidisciplinary teams to design and deploy impactful AI solutions in real-world scenarios.

• Lead the deployment and productionization of AI models in enterprise-grade environments, ensuring stability, scalability, and performance.
• Optimize inference pipelines through quantization, pruning, and tuning techniques to balance accuracy, latency, throughput, and energy consumption.
• Design, implement, and maintain inference services using tools such as Triton Inference Server and ONNX Runtime.
• Integrate AI models with specialized hardware accelerators to maximize execution efficiency.
• Develop monitoring, telemetry, and health-check systems for AI workloads in production.
• Perform profiling, benchmarking, and performance analysis to continuously improve system efficiency.
• Architect and support advanced AI use cases such as LLM serving, retrieval-augmented generation systems, copilots, and real-time video analytics.
• Build APIs and inference services using Python and C++, collaborating closely with data, ML, and engineering teams.

Requirements:

• Strong experience deploying and optimizing machine learning models in production environments.
• Solid expertise with PyTorch and TensorFlow, especially model export workflows.
• Deep understanding of ONNX and ONNX Runtime.
• Hands-on experience with inference servers such as Triton Inference Server.
• Strong knowledge of inference optimization techniques including INT8, FP16, and mixed precision.
• Advanced Python programming skills.
• Intermediate to advanced C++ skills with a focus on performance optimization.
• Experience working in Linux environments, Docker, and containerized infrastructures.
• Background in performance profiling, benchmarking, and system optimization.
• Familiarity with LLMs, vision models, NLP architectures, and multimodal AI systems.
• Experience in at least one of the following domains: GenAI at scale, real-time computer vision, edge AI systems, or large-scale NLP applications.
• Strong analytical thinking, autonomy, and ability to work in complex technical environments.
• Clear communication skills and ability to collaborate with cross-functional teams.

Benefits:

• Fully remote work model with occasional on-site visits in São Paulo when needed.
• Indefinite contract and long-term engagement.
• Opportunity to work on cutting-edge AI systems involving high-performance and edge computing.
• Exposure to advanced hardware acceleration technologies and large-scale AI deployments.
• Collaborative and technically challenging environment focused on innovation and impact.
• Strong engineering culture with emphasis on ownership, autonomy, and performance excellence.
• Competitive conditions aligned with senior-level technical expertise.