ML Infrastructure Engineer
Byteridge is hiring an ML Infrastructure Engineer in Bengaluru to focus on deploying and optimizing large language models for strategic customers. You will architect scalable ML pipelines using Amazon SageMaker and perform kernel-level GPU optimizations to improve performance. The role requires strong expertise in Python, ML frameworks, and deep experience with GPU computing and AWS infrastructure. You will work closely with customer teams to drive model performance benchmarking and infrastructure design.
50k new jobs listed every day. Install TAL to find more jobs like this.
Experience
5+ years
Function
Engineering
Work mode
Onsite, India
Company
Tier 2
What you will work on
Byteridge is hiring an ML Infrastructure Engineer in Bengaluru to focus on deploying and optimizing large language models for strategic customers. You will architect scalable ML pipelines using Amazon SageMaker and perform kernel-level GPU optimizations to improve performance. The role requires strong expertise in Python, ML frameworks, and deep experience with GPU computing and AWS infrastructure. You will work closely with customer teams to drive model performance benchmarking and infrastructure design.
TAL's take
Solid tier-2 company with a well-defined, highly technical role in AI/ML infrastructure.
The JD provides a very clear scope, specific technology stack, and well-articulated responsibilities.
Must haves
- 5+ years of experience in machine learning infrastructure or GPU computing
- Strong programming skills in Python
- Experience with ML frameworks like PyTorch, TensorFlow, or JAX
- Deep understanding of LLM architectures and inference optimization
- Proficiency with GPU programming and CUDA
Tools and skills
Nice to have: nvidia a100, nvidia h100, trainium, inferentia, mlops.
About the company
Established mid-stage software services and product development company.