Senior Software Engineer (AI Systems Performance) | Remote (Brazil)

Luxoft; Brasil; On-site; BRL 180,000 - 280,000; Full time

Job summary

Luxoft is seeking a Senior Software Engineer in Brazil to drive distributed AI performance on multi-GPU/multi-node systems. You will benchmark, debug, and optimize AI workloads, collaborate with GPU library teams, and advance model infrastructure and monitoring across scalable clusters.

The role requires hands-on experience with AI inference frameworks, KV cache transfer, and expert parallelization, plus strong C/C++ and Python skills. CLT-only Brazil employment with English CV submission.

Qualifications

• Hands-on experience with AI inference/serving frameworks such as vLLM, SGLang, and Llama.cpp.
• Understanding KV cache transfer mechanisms and expert parallelization (Mooncake, NIXL/RIXL, DeepEP, MORI, PPLX-Garden).
• Strong C/C++ and Python skills with software design, debugging, performance analysis, and test development.
• Experience running AI workloads on large-scale, heterogeneous compute clusters.
• Familiarity with cluster management and orchestration platforms such as SLURM and Kubernetes.
• Experience with CI/CD tools like GitHub and Jenkins.

Responsibilities

• Enable and benchmark AI models on large-scale distributed systems to evaluate performance, accuracy, and scalability.
• Optimize AI workloads across scale-up, scale-out, and scale-across configurations.
• Collaborate with internal GPU library teams to analyze and optimize distributed workloads for throughput and latency.
• Develop and apply parallelization strategies for AI workloads to achieve best-in-class performance across hardware topologies.
• Contribute to distributed model management systems, model zoos, monitoring, pipelines, and technical documentation.
• Build and maintain real-time dashboards reporting performance, accuracy, and reliability metrics for internal stakeholders and external users.

Tools

vLLM

SGLang

Llama.cpp

Mooncake

NIXL/RIXL

DeepEP

MORI

PPLX-Garden

SLURM

Kubernetes

GitHub

Jenkins

C/C++

Python

Job description

Contract Type: CLT Only (Luxoft operates exclusively under CLT in Brazil)

Language Requirement: Advanced / Fluent English (Please submit your CV in English)

About the Role & Project

Are you passionate about high-performance computing, distributed inferencing on GPUs, and pushing the boundaries of AI hardware and software?

We are partnering with a world-leading semiconductor and high-performance computing (HPC) company to tackle complex performance and scalability challenges in distributed AI systems. As a Senior Software Engineer, you will join a core team of elite industry specialists working with state-of-the-art hardware and software technologies to benchmark, debug, and optimize cutting-edge AI workloads on multi-GPU and multi-node clusters.

• Distributed AI Enablement & Benchmarking: Enable and benchmark AI models on large-scale distributed systems to evaluate performance, accuracy, and scalability.
• Scalable Systems Optimization: Optimize AI workloads across scale-up (multi-GPU), scale-out (multi-node), and scale-across distributed system configurations.
• Cross-Team Collaboration: Partner closely with internal GPU library teams to analyze and optimize distributed workloads for high throughput and ultra-low latency.
• Parallelization Strategies: Develop and apply optimal parallelization strategies for AI workloads to achieve best-in-class performance across diverse hardware topologies.
• Model Infrastructure & Management: Contribute to distributed model management systems, model zoos, monitoring frameworks, benchmarking pipelines, and technical documentation.
• Performance Monitoring & Visualization: Build and maintain real-time dashboards reporting performance, accuracy, and reliability metrics for internal stakeholders and external users.

Mandatory Skills & Qualifications

• AI Framework Engineering: Hands-on experience with AI inference or serving frameworks such as vLLM, SGLang, and Llama.cpp.
• KV Cache and Expert Parallelization: Understanding KV cache transfer mechanisms and technologies (e.g., Mooncake, NIXL/RIXL) and expert parallelization approaches (e.g., DeepEP, MORI, PPLX-Garden).
• Programming and Software Design: Strong C/C++ and Python skills, with experience in software design, debugging, performance analysis, and test development.
• Large-Scale Distributed Systems: Experience running AI workloads on large-scale, heterogeneous compute clusters.
• Cluster and Orchestration Systems: Familiarity with cluster management and orchestration platforms such as SLURM and Kubernetes (K8s).
• Development Tools and Workflows: Experience with GitHub, Jenkins, or similar CI/CD tools and modern development workflows.
• Contract Model: CLT Only (Exclusive Luxoft Brazil employment model).
• Resume: Candidates must apply with an English CV to be considered for client screening.

Ready to Drive Next-Gen AI Performance?