GPU/ML Systems Engineer

Experience: 3–7 years | Hands -on GPU
optimization required

Location: Office – Coimbatore/Bengaluru

Aivar is an AI -first technology partner where cutting -edge technology meets industry expertise to supercharge your projects. Our AI -augmented teams accelerate development, reduce time -to -market, and deliver exceptional code quality. We bring together the best minds in tech to craft scalable, repeatable solutions that drive real momentum for your business.

The specialist who takes AI
deployments from “it works” to “sub -second latency at 40% lower cost.” Own
vLLM/Triton configurations, model quantization (INT8, FP16, 4 -bit), tensor
parallelism on multi -GPU instances, AWS Inferentia optimization, and performance
benchmarking. Proven results: 40% cost reduction on Whisper ASR, 0.41s TTFT on
Llama 70B, 85% throughput gain on YOLO via Inferentia.

• Deploy and tune vLLM with multi -GPU tensor
  parallelism, dynamic batching, PagedAttention, and KV cache optimization for
  LLMs
  
• Configure NVIDIA Triton for production multi -model
  serving with custom backends and model ensembles
  
• Build TensorRT -LLM optimized model binaries for
  maximum throughput on L40S, A100, and H100 GPUs
  
• Implement AWS Inferentia deployments using Neuron SDK
  — model compilation, operator support, performance tuning
  
• Run comprehensive load testing (Locust) to map
  performance cliffs, optimal concurrency, and scaling thresholds
  
• Execute model quantization (INT8, FP16, GPTQ, AWQ)
  with rigorous quality -accuracy tradeoff analysis
  
• Produce detailed benchmark reports with instance
  selection, scaling strategy, and cost -per -token recommendations
  
• Neuron: Experience in optimizing models for custom
  accelerators like AWS Inferentia/Trainiums
  

• GPU -accelerated ML workloads in production (3+ years)
  
• LLM serving — vLLM, TensorRT -LLM, or Triton Inference
  Server (hands -on)
  
• GPU architecture — memory hierarchy, tensor cores,
  NVLink, NCCL multi -GPU communication
  
• Model quantization — INT8, FP16, mixed precision,
  GPTQ/AWQ
  
• CUDA ecosystem — drivers, cuDNN, NVIDIA container
  toolkit
  
• Performance engineering — profiling (Nsight,
  nvidia -smi, DCGM), bottleneck analysis, load testing
  
• AWS GPU instances — G -series (L40S), P -series (A100),
  instance selection methodology
  

vLLM, NVIDIA Triton, TensorRT -LLM,
KServe, CUDA/cuDNN/NCCL/DCGM, AWS Inferentia/Neuron SDK, GPTQ/AWQ/bitsandbytes,
Locust, Nsight Systems, Prometheus + DCGM Exporter, AWS (EC2 GPU, EKS, Capacity
Blocks)

Benefits

• Learn from Experts: Work directly with former AWS leaders and AI pioneers.
  
• Direct Ownership: Lead high -impact "greenfield" projects from concept to global launch.
  
• Modern Tech: Master the latest Generative AI frameworks and cloud -native architectures.
  
• Real -World Impact: Build mission -critical systems used by major global enterprises.
  
• Rapid Growth: Scale your career quickly in a high -speed
  

Diversity and Inclusion