Colorado - Basalt

10 Years

- /- ( )

Required Skills

Machine Learning Engineer

Work Authorization

  • US Citizen

  • Green Card

  • EAD (OPT/CPT/GC/H4)

  • H1B Work Permit

Preferred Employment

  • Corp-Corp

  • W2-Permanent

  • W2-Contract

  • Contract to Hire

Employment Type

  • Consulting/Contract

education qualification

  • UG :- - Not Required

  • PG :- - Not Required

Other Information

  • No of position :- ( 1 )

  • Post :- 28th May 2025

JOB DETAIL

  1. Experience with model serving frameworks:  
  2. TorchServe for PyTorch models
  3. TensorFlow Serving for TF models
  4. Triton Inference Server for multi-framework support
  5. BentoML for unified model serving
  6. Expertise in model runtime optimizations:  
  7. Model quantization (INT8, FP16)
  8. Model pruning and compression
  9. Kernel optimizations
  10. Batching strategies
  11. Hardware-specific optimizations (CPU/GPU)
  12. Experience with model inference workflows:  
  13. Pre/post-processing pipeline optimization
  14. Feature transformation at serving time
  15. Caching strategies for inference
  16. Multi-model inference orchestration
  17. Dynamic batching and request routing
  18. Experience with GPU infrastructure management
  19. Knowledge of low-latency serving architectures
  20. Familiarity with ML-specific security requirements
  21. Background in performance profiling and optimization
  22. Experience with model serving metrics collection and analysis.

Company Information

Aspired Solutions

saiteja.a@aspiredsolutions.com

9895751235