System Software Engineer (ai/ml) (job Code 93641)

AI Deployment Software Engineer

Duties: Develop, enhance, and maintain next-generation AI deployment software. Build and scale software deliverables in a tight development window. Build out the SW stack for d-Matrix's AI compute engine working closely with other software (ML, Systems) and hardware experts. Productize the software stack for our AI compute engine. Focus on the full stack chain tool and understand the nuances to optimize and trade-off various aspects of hardware-software co-design. Focus on system software, data structures, parallel programming, computer architecture, and machine learning fundamentals. Ensure that programs continue to function normally through software maintenance and testing. Analyze users' needs and then design and develop software to meet those needs and recommend software upgrades for customers' existing programs and systems.

Education Required: Master's degree or foreign equivalent in Computer Science, Computer Engineering, Electrical and Computer Engineering, or related field.

Experience Required: 2 years of experience as Software Engineer or related occupation.

Special Requirements: Must have at least 1 year of prior work experience in each of the following: 1. Programming using C, C++, and Golang and low-level debugging and system software development. 2. Distributed systems, including Kubernetes (K8s), LLM serving, finetuning, and infrastructure development. 3. Parallel programming using multithreading (pthread), performance optimization, and profiling using pprof, gperf, and FlameGraph. 4. System and hardware-level performance tuning to optimize throughput, latency, and resource utilization. 5. Workload offloading for high-performance computing using at least one of the following accelerators: DPU, TPU, or GPU. 6. Kubernetes, container orchestration, and container runtime internals including containerd, kata-containers, Docker, and KVM. 7. Designing, deploying, and customizing large-scale AI/ML infrastructure on Kubernetes from bare-metal machines.

Some telecommuting permitted (hybrid). Email resume to apply@d-matrix.ai. Must specify job code 93641 in reply. EOE.