Employer Active
Job Alert
You will be updated with latest job alerts via emailJob Alert
You will be updated with latest job alerts via email2-3years
Not Disclosed
Salary Not Disclosed
1 Vacancy
ACG2740JOB
Our client is a topnotch semiconductor manufacturing company who is looking for a qualified candidate to join their firm.
Design and implement system software to accelerate LLM inference particularly in PyTorchbased runtime environments.
Build and enhance networking modules to enable highspeed lowlatency data exchange across computing clusters.
Evaluate inference and AI/HPC workload performance through benchmarking and system profiling on target platforms.
Engineer efficient I/O scheduling mechanisms for streamlined data handling across compute nodes.
Manage and deploy software in Linuxbased environments.
Minimum 2 years of practical experience coding in Linuxbased systems.
Strong foundation in system architecture OS internals and network layers.
Handson knowledge of networking protocols and systemslevel communication frameworks.
Nice to have:
Experience with Linux kernel development or opensource kernel contributions.
Solid foundation in distributed systems and parallel computing models.
Understanding of AI systems especially involving large language model finetuning or inference platforms.
Awareness of RetrievalAugmented Generation (RAG) pipelines in the context of LLM architecture.
Ideal Candidate Traits:
Collaborative team player who proactively works across functions to solve technical challenges.
Openminded with strong team communication and mutual respect in shared decisions.
Confident communicator capable of bridging hardware and software development teams particularly across international teams (e.g. Korea).
Contact: Giang Tran or Giau Nguyen
Due to the immense number of applications only shortlisted candidates will be contacted.
Full Time