Work With Me
I'm Tanmay Mohan — a cloud physicist building GPU inference platforms, hardening EKS clusters, and optimizing cloud costs at scale.
🎯 Open To
| Type | Details |
|---|---|
| Full-time | Senior / Staff / Principal DevOps, Platform Engineer, MLOps Engineer, Cloud Architect |
| Contract / Consulting | GPU inference platform design, EKS security hardening, cloud cost optimization (FinOps), Kubernetes architecture reviews |
| Advisory | Technical due diligence, architecture decision records (ADRs), team upskilling |
| Speaking | Conferences, meetups, podcasts, internal tech talks |
💼 What I Bring
- Production GPU at scale: 116 GPUs (55× RTX PRO 6000 Blackwell) on EKS with $0 idle via scale-to-zero
- Cloud cost reduction: $20K+/year saved through right-sizing, Spot, Savings Plans, RI, ODCR, deprecation
- Security hardening: 4-week EKS plan — Bottlerocket, private API, IRSA, SonarCloud, Trivy, WAF, VAPT-ready
- Cross-cloud migration: 4 GPU workloads GCP→AWS in 4 weeks (Triton, vLLM, TensorRT-LLM, Whisper)
- Documentation & knowledge transfer: 4 doc series, 18+ blog posts, runbooks, checklists, diagrams
📩 Best Way to Reach Me
| Channel | Link |
|---|---|
tanmay [at] tanmaymohan.com | |
| linkedin.com/in/tanmaymohan | |
| GitHub | github.com/tanmaymohan |
| Portfolio | tanmaymohan.com |
🕐 Response Time
I typically respond within 24 hours on weekdays. If you don't hear back, ping me on LinkedIn — sometimes email gets caught in filters.
🤝 Let's Talk If You're
- Building GPU inference infrastructure and need Karpenter/KEDA patterns
- Facing an EKS security audit or VAPT
- Watching cloud bills climb and need a systematic FinOps approach
- Migrating workloads across clouds or to Kubernetes
- Looking for a platform engineer who writes, diagrams, and teaches
Prefer a quick call? Book 15 mins: calendly.com/tanmaymohan (add link when ready)