Your Name
MLOps Engineer / AI Platform Engineer
City, India · +91 98XXX XXXXX · your.name@email.com · linkedin.com/in/yourname · github.com/yourname
Professional Summary
Platform engineer with 8 years in DevOps and SRE, now building infrastructure for ML and LLM workloads. Runs a Kubernetes based Model Serving platform with vLLM on GPU nodes for 6 product teams, with autoscaling, an LLM gateway and cost observability. Brings production reliability, CI/CD and Terraform discipline to MLOps.
Skills
- Infrastructure: Kubernetes, Docker, Helm, Terraform, AWS (EKS, EC2, S3), GPU scheduling
- MLOps & Serving: MLOps, Model Serving, vLLM, KServe, MLflow, Model Registry, CI/CD (GitHub Actions, Argo CD)
- Observability: Prometheus, Grafana, OpenTelemetry, Observability, SLOs, on call
- Languages: Python, Go, Bash
Professional Experience
Senior Platform Engineer (AI Infrastructure), Northwind Payments Pvt. Ltd., Bengaluru Feb 2022 to Present
- Built a Kubernetes Model Serving platform with vLLM on GPU node pools for 6 teams; raised GPU utilisation from 22% to 68%.
- Introduced an LLM gateway with per team rate limits, budgets and provider fallback, cutting monthly LLM spend by ₹18 lakh.
- Automated ML training and promotion pipelines with CI/CD, MLflow and a Model Registry, reducing model release time from 2 weeks to 1 day.
- Defined SLOs and Observability dashboards in Prometheus and Grafana (time to first token, p95 latency, cost per request).
- Codified all infrastructure in Terraform and Helm charts, enabling new environments in 30 minutes.
DevOps Engineer, Fabrikam Logistics, Chennai Jun 2017 to Jan 2022
- Migrated 80 services to Docker and Kubernetes (EKS), improving deployment frequency 5x.
- Led incident response for a 24×7 platform, reducing MTTR from 70 to 20 minutes.
Projects
LLM Serving Benchmark · vLLM, Kubernetes, Python github.com/yourname/LlmServingBench
- Benchmarked TTFT, tokens/sec and cost per 1,000 requests across batch sizes and GPUs; published a self host vs API decision guide.
Education
B.E., Computer Engineering, Your University · 2017
Certifications
- Certified Kubernetes Administrator (CKA)
- AWS Certified DevOps Engineer Professional