SRE Copilot
AI observability chat assistant for root-cause analysis. Natural-language querying of metrics, logs and traces across Datadog APM, Kubernetes and PagerDuty.
Claude SonnetLangGraph
DatadogKubernetesMCP
available for senior SRE / platform / AI-infra roles · Mesa, AZ · remote
Neel Thomas_
$ devops · sre · aiops engineer
10+ years building scalable, reliable cloud-native infrastructure and internal platforms — supporting 100M+ users. Now focused on AI infrastructure, AIOps, and MCP platforms that put LLMs to work in production SRE workflows.
10+
years in DevOps / SRE
100M+
users supported
6TB+
logs / day pipelined
125+
k8s services observed
Selected work · AI-Core / AIOps
Putting LLMs to work in production SRE
Tools I built at Life360 to drive AI adoption across infrastructure — Eagle-Eye open-sourced as an MCP server with growing community traction (10+ stars).
Eagle-Eye
Single-pane-of-glass for on-call engineers — unifies metrics, logs, alerts and debugging context so responders stop tab-hopping during incidents.
ObservabilityMCP
Incident responseOn-call
Claude Code Observability
Self-hosted Grafana + OTEL stack to track Claude Code CLI cost and token
usage — uniquely captures skill/tool invocation analytics. One make up
spins up Prometheus, Grafana, Loki and an OTEL Collector with pre-built dashboards.
Local-only; no SaaS, no data egress.
GrafanaOpenTelemetry
PrometheusLokiDocker
Forecasting MCP
Capacity-planning MCP over Datadog time-series + Facebook Prophet to forecast traffic spikes and proactively size CPU, memory and HPA for peak events.
ProphetTime-series
HPAForecasting
SLICK — Streamlit One-Click
Vibe-coding platform on top of the existing GitOps stack for one-click deploys of AI apps. Adopted by 10+ internal teams; biggest win in Ads & Marketing.
StreamlitGitOps
Databricks MCPFunction calling
Career log
Experience
Sr Software Engineer, DevOps · Life360
Aug 2025 — Present
Cloud Success team — CI/CD, observability and release pipelines. Built Eagle-Eye (open-sourced MCP server, 10+ stars), a Prophet-based capacity-planning MCP and the SLICK platform; evaluated 30+ AI dev tools and provisioned a dedicated EKS cluster for MCP workloads.
Sr Software Engineer, Network Operations · Life360
Jun 2023 — Jul 2025
Owned observability for 125+ k8s services supporting 100M+ users. Replaced logging agents with Vector (6TB+/day), ran Prometheus on EKS, led an OpenTelemetry PoC and eBPF service mapping.
DevOps Engineer · Dview.io
Nov 2022 — May 2023
Founding engineer at a pre-seed data platform. Built full AWS infra with Terraform/Terragrunt/Atlantis, multi-region EKS, ArgoCD GitOps and SLI/SLO frameworks.
DevOps Consultant · Freelance
May 2022 — Nov 2022
End-to-end cloud & Kubernetes infrastructure for startups; DevOps advisory to 5+ SaaS portfolio companies under Together Fund.
Site Reliability Engineer · Zolve
Apr 2021 — May 2022
Built the entire cloud + Kubernetes platform for a $210M neobank — 20+ microservices on multi-region EKS, CI/CD, GitOps and Prometheus/Grafana observability.
Site Reliability Engineer · Careem (an Uber company)
Sep 2019 — Sep 2020
Delivered AWS cost optimizations saving $336K/yr for Careem Pay. Migrated production from Elastic Beanstalk to EKS; 24/7 on-call.
DevOps Engineer · Ola Cabs
Oct 2017 — Aug 2019
Ran large-scale CI/CD on Jenkins + Mesos; migrated payment workloads AWS→Azure for ~20% infra savings.
Linux System Engineer · Poornam Info Vision
May 2015 — Sep 2017
Linux administration for 25+ global clients; handled security incidents — spam, spoofing and intrusion mitigation.
Toolchain
Skills
Languages & IaC
GoBashTerraform
TerragruntCloudFormation
Cloud & Kubernetes
AWSAzureEKS
ArgoCDArgo RolloutsKEDA
KyvernoIstioKarpenter
Observability
PrometheusGrafanaDatadog
New RelicVectorOpenTelemetry
eBPF
AI Infrastructure
MCPClaudeLangGraph
RAGProphetLangfuse
Streamlit
Let's talk
Building reliable systems —
now with AI in the loop.
Open to senior SRE, platform and AI-infrastructure roles. The fastest way to reach me is email.