Jobs

Interviews
Job Alerts
Tools

Upskill and Grow with AI

Mock Interview Practice interviews in realistic simulations

Coding Practice Improve your coding skills with challenges

Certification Earn certifications to validate your skills

AI Learning Get trained with AI expert sessions

Career Path AI insights for smarter career decisions

AI Job Match Score AI-Powered Job Match Against Your Resume and Optimize Your Resume

Career Tools and Resources

Resume Builder Build Professional Resume with Ease

ATS Friendliness Check Check Resume Friendliness for Applicant Tracking Systems

Auto Apply Apply to hundreds of jobs on any platform effortlessly

Co-Pilot (Chrome Extension) Your AI Assistant for Seamless Browsing Efficiency

Interview Questions Streamline interviews with ready-to-use questions

Salaries Discover market-driven salary insights across skillsets and geographies

Companies Explore leading companies actively hiring talent
For Employers

Home
>
Jobs in vadodara
>
Dharmakit Networks
>
GPU Infrastructure Engineer

GPU Infrastructure Engineer

Dharmakit Networks

3 - 7 years

0 Lacs

vadodara gujarat

Posted:3 days ago| Platform: Shine logo

Apply

Skills Required

monitoring kubernetes logging pruning gcp cuda ci batch processing cloud ml microsoft azure git agile pipelines aws gpu google cloud platform optimization azure docker cd cost optimization infrastructure hugging face triton cloudwatch infrastructure monitoring nvidia gpus nvidia nvcf int8 deepspeed offline ai problemsolving data processing workflows grafana ai ethics ai governance elk stack onnx quantization ml model deployment backend apis nvidia prometheus deep learning model deployment ml pipelines automated ml workflows tensorrt vllm terraform edge deployments batch ai processing model cicd fp16 model cicd pipelines ai

Work Mode

On-site

Job Type

Full Time

Job Description

Role Overview: As a GPU Infrastructure Engineer at Dharmakit Networks, you will play a crucial role in building, optimizing, and scaling the GPU and AI compute infrastructure for Project Ax1. Your responsibilities will include managing cloud and on-prem clusters, setting up model CI/CD pipelines, and ensuring efficient utilization of GPUs to support AI systems. Key Responsibilities: - Design, deploy, and optimize GPU infrastructure for large-scale AI workloads. - Manage GPU clusters across cloud platforms such as AWS, Azure, and GCP, as well as on-prem setups. - Set up and maintain model CI/CD pipelines to streamline training and deployment processes. - Optimize LLM inference using technologies like TensorRT, ONNX, and Nvidia NVCF. - Handle offline/edge deployments of AI models using tools like CUDA, Lambda, and containerized AI. - Build and fine-tune data pipelines to support real-time and batch processing. - Monitor model and infrastructure performance to ensure availability, latency, and cost efficiency. - Implement logging, monitoring, and alerting mechanisms using Prometheus, Grafana, ELK, and CloudWatch. - Collaborate closely with AI Experts, ML Experts, backend Experts, and full-stack teams to ensure smooth model delivery. Qualifications Required: - Bachelor's degree in Computer Science, Engineering, or a related field. - Hands-on experience with Nvidia GPUs, CUDA, and deep learning model deployment. - Strong proficiency in setting up and scaling AWS, Azure, or GCP GPU instances. - Expertise in model CI/CD and automated ML workflows. - Familiarity with tools like Terraform, Kubernetes, and Docker. - Knowledge of offline/edge AI deployment, including quantization and optimization techniques. - Experience in logging & monitoring using tools such as Prometheus, Grafana, and CloudWatch. - Proficiency in backend APIs, data processing workflows, and ML pipelines. - Familiarity with version control using Git, collaboration in agile environments, and working in cross-functional teams. - Strong analytical and debugging skills, along with excellent communication and problem-solving abilities. Good To Have: - Experience with technologies like Nvidia NVCF, DeepSpeed, vLLM, and Hugging Face Triton. - Knowledge of FP16/INT8 quantization, pruning, and other optimization strategies. - Exposure to serverless AI inference platforms such as Lambda, SageMaker, and Azure ML. - Contributions to open-source AI infrastructure projects or a strong GitHub portfolio demonstrating expertise in ML model deployment.,

More Jobs at Dharmakit Networks

Backend Engineer

Vadodara, Gujarat, India

Experience: Not specified

Salary: Not disclosed

Backend Engineer - RAG & ML specialisation

Vadodara, Gujarat, India

Experience: Not specified

Salary: Not disclosed

WordPress Developer Internship (Remote, Unpaid)

India

Experience: Not specified

Salary: Not disclosed

DevOps Engineer

Vadodara, Gujarat, India

Experience: Not specified

Salary: Not disclosed

WordPress Development Internship

India

Experience: Not specified

Salary: Not disclosed

Mock Interview

Practice Video Interview with JobPe AI

Start Job-Specific Interview

Start Your Job Search Today

Browse through a variety of job opportunities tailored to your skills and preferences. Filter by location, experience, salary, and more to find your perfect fit.

Job Application AI Bot

Apply to 20+ Portals in one click

Download Now

Download the Mobile App

Instantly access job listings, apply easily, and track applications.

Enhance Your Skills

Practice coding challenges to boost your skills

Start Practicing Now

Dharmakit Networks

Login to

Please Verify Your Phone or Email

Confirm Action

GPU Infrastructure Engineer