Job Summary

Develop high-performance AI models optimized for specific hardware architectures, including CPUs and GPUs. Implement mathematical constructs from scratch using processor-specific instruction sets. Build efficient memory-management modules tailored for performance-critical applications. Write and optimize parallel programming code to ensure maximum throughput and scalability. Collaborate closely with the Algorithm and AI Research team to integrate advanced techniques into production systems. Work alongside highly skilled teammates with strong expertise in C++ and systems programming. Mentor, guide, and review the code of colleagues with less experience in C/C++. Ensure high coding standards, performance, and reliability across all development tasks. Strong working knowledge of C/C++ experience with Linux Kernel or other embedded systems, Kernel, Memory Management, Paging, Cache memory, low-level code, and processor intrinsics.

Algorithm

Design and Analysis. Hands-on with Compiler Optimisations, especially gcc. Parallel and Concurrent programming.

Designed

Lockfree, Lockless Data Structures.

Experience in debugging parallel code, especially with gdb. Working knowledge of OpenMPI is a must. High-performance computing experience, such as optimised MATMUL, is good to have. We are looking for a skilled C++ Developer to join our development team.

In this role, you will develop high-performance AI models on specific hardware architectures, such as CPUs and GPUs. You will implement several mathematical constructs from scratch, using processor-specific instruction sets, and build productive memory management modules. Most code will require parallel programming.

You will coordinate with the Algorithm and AI research team,



and your fellow teammates will include individuals who are of the same calibre as you. You may also have to mentor, manage and review the code of your colleagues who have relatively less experience in C/C++ than you.

Responsibilities

- Develop high-performance AI models optimized for specific hardware architectures, including CPUs and GPUs.
- Implement mathematical constructs from scratch using processor-specific instruction sets.
- Build efficient memory-management modules tailored for performance-critical applications.
- Write and optimize parallel programming code to ensure maximum throughput and scalability.
- Collaborate closely with the Algorithm and AI Research team to integrate advanced techniques into production systems.
- Work alongside highly skilled teammates with strong expertise in C++ and systems programming.
- Mentor, guide, and review the code of colleagues with less experience in C/C++.
- Ensure high coding standards, performance, and reliability across all development tasks.

Requirements

- Strong working knowledge of C/C++
- Experience with Linux Kernel or other embedded systems, Kernel, Memory Management, Paging, Cache memory, low-level code, and processor intrinsics.
- Algorithm Design and Analysis.
- Hands-on with Compiler Optimisations, especially gcc.
- Parallel and Concurrent programming.
- Designed Lockfree, Lockless Data Structures.
- Experience in debugging parallel code, especially with gdb.
- Working knowledge of OpenMPI is a must.
- High-performance computing experience, such as optimised MATMUL, is good to have.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 C/C++ Developer (Bengaluru)
🏢 Ziroh Labs
📍 Bengaluru