Kategorien durchsuchen
Entdecken
Fiverr Pro
Deutsch
$
USD
Jagmeet S
@jagga5025
Tech Lead AI Infrastructure Engineer
Indien
Englisch, Hindi, Punjabi
Über mich
I’m an AI Infrastructure Engineer and Tech Lead with 5+ years of experience building scalable AI platforms, GPU infrastructure, Kubernetes environments, distributed ML systems, and LLM serving platforms. I specialize in Python, Kubernetes, Docker, PyTorch, vLLM, NCCL, Megatron-LM, MLOps, and AI infrastructure optimization. I’ve worked on platforms supporting 1024+ GPUs and 200+ AI/LLM models. I can help with LLM deployment, GPU infrastructure, Kubernetes troubleshooting, distributed training, automation, and production-ready AI solutions.
Kompetenzen
Jagmeet S
offline •
Durchschnittliche Antwortzeit: 1 Stunde
Meine Dienstleistungen
KI-Implementierung und -Bereitstellung
I will deploy and configure your llm using vllm, docker and kubernetes
DevOps-Containerisierung
I will troubleshoot and optimize your kubernetes infrastructure
Portfolio
Arbeitserfahrung
E2E Networks Limited
Vollzeit • 5 yrs
Lead Engineer
Apr 2025 - Present • 1 yr 5 mos
Lead the architecture and deployment of large-scale AI infrastructure supporting 1024+ GPUs. Designed high-performance networking using InfiniBand and GPUDirect RDMA, improving throughput by 35%. Built enterprise AI platforms supporting 100+ users and 200+ LLM models. Developed observability frameworks for Kubernetes-based clusters and optimized distributed workloads using PyTorch and Megatron-LM.
Senior Software Engineer
Apr 2024 - Mar 2025 • 11 mos
Led the development of the Tier AI/ML Platform, reducing model training time by 30%. Built a containerized Jupyter Notebook platform for 100+ concurrent users. Spearheaded LLM serving and Kubernetes-based serverless inference, enabling deployment of 200+ models while reducing infrastructure costs by 40% through automatic scale-to-zero functionality.
Software Engineer
Jul 2021 - Mar 2024 • 2 yrs 8 mos
Contributed to a managed RDS platform supporting PostgreSQL, MySQL, and MariaDB, achieving 99.9% uptime. Enhanced reliability through centralized logging and OpenNebula-based snapshots. Designed Django-based microservices and automation systems, optimizing data processing through RabbitMQ and Elasticsearch integrations.
