AI Systems Architecture Engineer – Lead Senior Engineer/Senior Engineer

Overview

Define, prototype, and optimize next-generation AI computing systems across heterogeneous hardware and software platforms, focusing on how AI workloads use system resources to maximize performance, power efficiency, scalability, and platform utilization.

What you'll do

• Define and evaluate system architectures for AI platforms incorporating heterogeneous compute elements such as CPU, NPU, GPU, memory interconnects and subsystems.
• Use profiling and modeling tools to understand optimal use of resources for best system performance.
• Develop system-architecture prototypes to evaluate workload partitioning across compute engines, data movement and memory traffic, compute and memory bottlenecks, scheduling and resource allocation, and power, thermal, and performance tradeoffs.
• Analyze AI workloads to determine the best utilization of available architectural compute and memory resources.
• Investigate end-to-end AI execution pipelines, including model compilation and graph partitioning, runtime scheduling, kernel selection, memory allocation, data transfers, synchronization, and accelerator utilization.
• Build analytical models, simulators, emulators, and proof-of-concept implementations to assess architectural concepts before hardware availability.
• Evaluate the impact of system-level parameters such as compute throughput, memory bandwidth, cache and local memory capacity, interconnect bandwidth and latency, DMA and data-transfer efficiency, and accelerator occupancy.
• Identify performance bottlenecks and recommend architectural improvements based on workload characterization, profiling data, and benchmark results.
• Collaborate with hardware architects, AI accelerator designers, compiler teams, runtime engineers, firmware developers, performance engineers, and product teams.
• Define workload-driven architectural requirements and translate them into platform-level specifications.
• Develop technical proposals, architecture studies, tradeoff analyses, and performance projections for future AI platforms.

What you'll need

• Bachelor's or Master's degree in Computer Engineering, Electrical Engineering, Computer Science, or a related field.
• Strong programming skills in C, C++, and Python.
• Experience in one or more of: AI or machine-learning systems, computer architecture, heterogeneous computing, SoC architecture, accelerator architecture, high-performance computing, embedded systems, system performance analysis.
• 3-7 years of experience in a hardware-focused system optimization role (hiring across multiple levels).
• Strong understanding of computer architecture concepts.
• Ability to develop quantitative models and make architecture recommendations based on empirical data.
• Excellent written and verbal communication skills.
• Demonstrated ability to learn quickly, think critically, and adapt in a fast-paced, rapidly evolving technology environment.
• Minimum qualifications: Bachelor's degree in Engineering, Information Systems, Computer Science, or related field and 2+ years of software engineering or related work experience, OR Master's degree in the same fields and 1+ year of software engineering or related work experience, OR PhD in the same fields.
• Minimum qualifications: 2+ years of academic or work experience with a programming language such as C, C++, Java, or Python.

Nice to have

• Experience with AI-specific performance optimization.
• Hands-on experience optimizing AI models for performance, power, and accuracy on hardware accelerators such as CPUs, GPUs, and NPUs.
• Experience using processor-specific optimization tools, libraries, and profiling technologies to improve AI performance on CPUs, GPUs, and NPUs.
• Strong understanding of modern machine learning architectures, including CNNs, RNNs, Transformers, and ensemble methods.
• Proficiency with AI frameworks and tooling such as PyTorch, TensorFlow, ONNX Runtime, and MLIR.
• Experience with transformer-based models such as BERT, GPT, T5, and Llama.
• Experience developing, optimizing, or deploying large language models (LLMs) or foundation models.

Details

• Location: Bangalore, India.