AI Infra Engineer focused on MLOps, AI Infrastructure and LLM Inference Engineering. My journey started with software development and machine learning and has evolved into building and operating production-grade infrastructure for GPU workloads, model serving and distributed AI systems.

I enjoy working at the intersection of Kubernetes, cloud infrastructure, machine learning and high-performance inference, with a strong interest in understanding how systems behave from the application layer all the way down to GPUs, networking and underlying infrastructure.

• 💻 Cloud Infrastructure Engineer at Simplismart, working on AI/ML Infrastructure & LLM Inference.
• 🚀 Building infrastructure for large-scale GPU workloads and production model serving.
• ☸️ Working extensively with Kubernetes, Helm, ArgoCD, KEDA and cloud infrastructure.
• 🧠 Exploring LLM inference, vLLM, Dynamo, distributed inference and performance optimization.
• ⚡ Working with NVIDIA GPUs including H100, B200 and L40S and GPU-aware scheduling.
• 📊 Building observability platforms using Prometheus, Grafana, Mimir, Loki, Alloy and NVIDIA DCGM.
• ☁️ Hands-on experience across AWS, Azure, GCP and on-prem infrastructure.
• 📫 How to reach me: adityakrishnanp007@gmail.com
• 🌱 Currently learning more about Inference Engineering, Distributed Systems, GPU Architecture and ML Systems.
• 💬 Ask me about Kubernetes, MLOps, GPU Infrastructure, LLM Serving, Python, Linux and Cloud Infrastructure.
• ⚡ Fun fact: I ❤️ to understand what happens under the hood.

• 💻 Languages: Python, Go, C/C++, Java, Dart, Bash.
• 🤖 AI / ML: LLM Inference, vLLM, Dynamo, MLflow, TensorFlow/Keras, NLP.
• ☸️ Infrastructure: Kubernetes, Docker, Helm, ArgoCD, KEDA, Istio.
• ⚡ GPU / Inference: NVIDIA H100, B200, L40S, GPU Scheduling, Distributed Inference, Model Serving.
• 📊 Observability: Prometheus, Grafana, Mimir, Loki, Alloy, NVIDIA DCGM.
• ☁️ Cloud: AWS, Azure, GCP, Terraform.
• 🗄️ Database / Storage: MySQL, MongoDB, Firebase, Weka.
• 🔄 CI/CD & VCS: GitHub, GitLab, Bitbucket, GitHub Actions, Jenkins.
• 🐧 OS & Systems: Linux, Kubernetes/containerd, Networking, Linux Systems.
• 🛠️ Engineering: Automation, Performance Debugging, Incident Response, RCA.