Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am an AI Platform Engineer focused on Kubernetes-based orchestration of LLM inference APIs in production, with hands-on experience in Helm, ArgoCD, and AWS. I thrive on building high-availability, scalable inference services with strong observability and platform reliability for enterprise AI deployments. In addition to designing robust pipelines and cloud infrastructure, I collaborate across teams to drive incident resilience, optimize deployments, and deliver measurable improvements in throughput and latency under variable load.…I am an AI Platform Engineer focused on Kubernetes-based orchestration of LLM inference APIs in production, with hands-on experience in Helm, ArgoCD, and AWS. I thrive on building high-availability, scalable inference services with strong observability and platform reliability for enterprise AI deployments. In addition to designing robust pipelines and cloud infrastructure, I collaborate across teams to drive incident resilience, optimize deployments, and deliver measurable improvements in throughput and latency under variable load.

Anirudh Narkedamilly

Cloud Developer, Full Stack Developer, Back-End Developer, +2





I am an AI Platform Engineer focused on Kubernetes-based orchestration of LLM inference APIs in production, with hands-on experience in Helm, ArgoCD, and AWS. I thrive on building high-availability, scalable inference services with strong observability and platform reliability for enterprise AI deployments. In addition to designing robust pipelines and cloud infrastructure, I collaborate across teams to drive incident resilience, optimize deployments, and deliver measurable improvements in throughput and latency under variable load.…I am an AI Platform Engineer focused on Kubernetes-based orchestration of LLM inference APIs in production, with hands-on experience in Helm, ArgoCD, and AWS. I thrive on building high-availability, scalable inference services with strong observability and platform reliability for enterprise AI deployments. In addition to designing robust pipelines and cloud infrastructure, I collaborate across teams to drive incident resilience, optimize deployments, and deliver measurable improvements in throughput and latency under variable load.

Available to hire

I am an AI Platform Engineer focused on Kubernetes-based orchestration of LLM inference APIs in production, with hands-on experience in Helm, ArgoCD, and AWS. I thrive on building high-availability, scalable inference services with strong observability and platform reliability for enterprise AI deployments.

In addition to designing robust pipelines and cloud infrastructure, I collaborate across teams to drive incident resilience, optimize deployments, and deliver measurable improvements in throughput and latency under variable load.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

Software Developer at Rebecca Everlene Trust Company

September 1, 2025 - Present

Led integration of inference-oriented API services using Python, containerized workloads, and structured request validation to support scalable processing patterns, reduced incident triage time by 31%, and strengthened production-grade deployment stability. Managed containerized workloads with Docker and CI/CD pipelines to enforce version-controlled releases, automated build verification, environment promotion governance, and consistent deployment behavior across staging and production Kubernetes clusters. Implemented monitoring and alerting solutions using CloudWatch metrics, centralized structured logging, and dashboards to enhance observability, ensure high availability, and proactively detect performance degradation in distributed inference-style services. Optimized AWS infrastructure with IAM policy hardening, compute scaling strategies, and configuration baselines to improve reliability and throughput under variable traffic.

Software Engineer at ENH iSecure

November 1, 2022 - November 1, 2023

Developed Python automation scripts and REST API integrations to orchestrate enterprise identity provisioning workflows, streamline multi-system coordination, and decrease manual ticket resolution time across distributed application environments. Improved deployment reliability using regression validation, configuration comparison, and structured release governance controls to reduce post-release defects and increase confidence in production rollouts. Maintained Linux-based backend services using log diagnostics, performance tracing, and runtime configuration tuning to troubleshoot integration failures and sustain stability under high-volume workloads. Collaborated with infrastructure and backend teams to coordinate deployment readiness and strengthen cross-functional delivery of secure, scalable platform services for enterprise clients.

AI Research Intern at Centre of Excellence in Artificial Intelligence, GITAM

August 1, 2021 - August 1, 2022

Built model-serving prototypes using Python and PyTorch to expose inference APIs for controlled evaluation scenarios, standardized deployment-style experimentation, and improved experiment throughput through reusable modular components. Benchmarked deep learning workloads with performance profiling and systematic validation to improve evaluation accuracy. Documented reproducible experiment workflows with structured reports, dashboards, and artifact versioning to support validation of generative AI research and collaborative reviews.