Accelerated Computing Engineer

We seek a driven Accelerated Computing Engineer to join our innovative team in Vellore. This entry-level role offers a unique opportunity to work with advanced AI/ML models, accelerated computing technologies, and cloud infrastructure while collaborating on cutting-edge research and deployment projects. You will work with a variety of state-of-the-art models such as BGE-Large, Mixtral, Gemma, LLaMA, and Stable Diffusion, as well as other fine-tuned architectures, to solve real-world computing challenges through advanced AI/ML infrastructure solutions.

Job Responsibilities

needs, translating them into robust, AI-driven solutions.

Model Deployment & Optimization: Develop and deploy advanced AI/ML models such as LLaMA,

Mixtral, Gemma, and other GenAI models while optimizing their performance for varied computing

environments.

Performance Testing & System Benchmarking: Execute advanced test scenarios and performance

benchmarks across AI/ML models and distributed systems to ensure optimal performance.

Infrastructure & Model Research: Research, configure, and maintain infrastructure solutions (using

tools like TensorRT and PyTorch) supporting our models and accelerated computing workloads.

AI/ML Model Integration: Support and deploy models such as Stable Diffusion, BGE, Mistral, and

custom fine-tuned models into end-to-end pipelines for AI/ML-driven solutions.

Automation & Process Improvements: Drive automation strategies to streamline workflows,

improve testing accuracy, and optimize system performance.

Technical Liaison: Served as the technical bridge by collaborating with product development

teams, tracking customer feedback, and ensuring timely resolutions.

Model Configuration & Troubleshooting: Create custom scripts, troubleshoot advanced

configurations, and support tuning efforts for AI/ML model customization.

Skills & QualificationsRequired Skills:

discipline.

Strong foundational knowledge of AI/ML model deployment and cloud infrastructure. Proficiency

with AI/ML frameworks & libraries, including PyTorch, TensorRT, and Triton.

Hands-on experience with deployment models such as LLaMA, Mixtral, Gemma, and Stable

Diffusion.

Familiarity with distributed computing environments and orchestration tools like Kubernetes.

Proficiency in workflow automation, performance tuning, and large-scale system debugging.

Understanding of cloud computing technologies and infrastructure architecture, including storage,

networking, and computing paradigms.

Preferred Skills:

MinIO.

Familiarity with advanced AI/ML model frameworks such as Gemma-2b, Mixtral-8x7b

Mistral-7b-instruct, and other fine-tuned AI models.

Expertise in GPU configuration and tuning for AI/ML workloads, including drivers and machine

learning optimization strategies.

Familiarity with serverless computing and Function as a Service (FaaS) concepts. Experience

with infrastructure as code (IaC) and performance benchmarking methodologies