AI Benchmarking & Performance Engineer

Sunrise Biztech Systems; Bangalore Rural; On-site; INR 1,400,000 - 2,300,000; Full time

Job summary

Sunrise Biztech Systems seeks an experienced AI Benchmarking & Performance Engineer to measure, analyze, and optimize AI model performance across CPUs, GPUs, and NPUs. Real‑world workloads in vision, speech, and robotics will be the focus, with emphasis on end‑to‑end performance in edge deployments.

You will set up repeatable benchmarking pipelines, profile across platforms, and deliver insights through technical reports to stakeholders.

Qualifications

• Experience in benchmarking AI workloads across CPU, GPU, and accelerator platforms.
• Strong understanding of AI/ML models and inference frameworks (PyTorch, ONNX, Linux).
• Experience with Linux systems and performance tools.
• Knowledge of CPU/GPU/NPU architectures and memory systems.
• Proficiency with profiling tools such as perf, VTune, Nsight.
• Proficient in C/C++ and Python; able to optimize code paths for AI workloads.

Responsibilities

• Benchmark AI workloads like YOLOv8, Whisper, and related models across platforms.
• Measure latency, throughput, memory usage, and power efficiency.
• Set up repeatable benchmarking pipelines on diverse hardware.
• Identify bottlenecks in CPU, GPU, memory, and data pipelines.
• Optimize models and pipelines using profiling and tuning techniques.
• Integrate models into robotics/edge AI workflows and assess end‑to‑end performance.
• Compare performance across AMD, NVIDIA, Qualcomm platforms and derive insights.
• Automate benchmark execution, data collection, and reporting.
• Prepare clear technical reports and performance summaries for stakeholders.

Skills

Performance benchmarking

System analysis

PyTorch

ONNX

Linux

Profiling tools

C/C++

Python

Edge AI workflows

Cross‑platform benchmarking

Tools

perf

VTune

Nsight

Linux performance tools

Job description

We are looking for an experienced AI Benchmarking & Performance Engineer to measure, analyze, and optimize AI model performance across modern computing platforms (CPU, GPU, and NPU). This role focuses on real-world AI workloads including vision, speech, and robotics models.

Key Responsibilities

• Benchmark AI, OpenVLA, YOLOv8, Whisper, Pi Droid, Groot, MLPerf Client and similar workloads
• Measure performance metrics including latency, throughput (FPS), memory usage, and power efficiency
• Set up and run repeatable benchmarking pipelines across different hardware platforms
• Perform system-level analysis to identify bottlenecks in CPU, GPU, memory, and data pipelines
• Optimize AI models and pipelines using profiling tools and performance tuning techniques
• Integrate AI models into application pipelines (e.g., robotics, edge AI workflows) and measure end-to-end performance
• Compare performance across platforms (AMD, NVIDIA, Qualcomm, etc.) and generate competitive insights
• Automate benchmark execution, data collection, and reporting
• Prepare clear technical reports and performance summaries for stakeholders

Required Skills

• Strong experience in performance benchmarking and system analysis
• Good understanding of AI/ML models and inference frameworks (PyTorch, ONNX,linux systems, AMD, NVIDIA, Qualcomm, robotics, edge AI workflows etc.)
• Experience with Linux systems and performance tools
• Knowledge of CPU/GPU/NPI architectures and memory systems
• Experience with profiling tools such as perf, VTune, Nsight or similar
• Programming proficiency in C/C++, Python/Peral.

Preferred Skills

• Experience with robotics or edge AI pipelines
• Experience with simulation environments or real-world deployment