AVAILABLE FOR CONTRACT & FREELANCE WORK

DevSecOps & AI Infrastructure Engineer

I build secure, autoscaling Kubernetes platforms, shift-left CI/CD pipelines, and production LLM / agentic-AI infrastructure — with security wired in from commit to cluster.

📍 London, UK — remote or on-site 🕐 7+ years in IT & cloud-native ⚡ Outside IR35 / day rate

Proven impact

Quantified results from production cloud-native platform engineering.

50%
Faster deployments
75%
Higher deploy frequency
40%
Cloud cost reduction
14
Open-source platforms shipped

What my tooling actually outputs

Anyone can list technologies. This is a real run of Forward-Deployed Preflight against a customer environment — every blocker gathered in one pass, each with the specific remedy and the team that owns it.

preflight — acme-staging
$ python main.py --profile examples/acme-staging.yaml --skip-tags k8s,llm

Preflight — acme-staging
========================

[FAIL] dns                  2 of 3 required hostname(s) do not resolve
           -> Add these names to the resolver used by the deployment target (not
              just the engineer's laptop — split-horizon DNS resolves differently
              per network segment). If they are public names, check whether egress
              DNS is restricted to an internal forwarder:
              registry.acme-internal.net, postgres.staging.acme-internal.net
[FAIL] tcp                  2 of 3 endpoint(s) unreachable
           -> Request an egress allow-rule for these host:port pairs from the
              network team, from the subnet the workload will actually run in. A
              'connection refused' means something answered and declined (likely
              the right path, wrong port); a timeout means the packets were
              dropped (firewall).
[ok  ] tls_interception     TLS to api.anthropic.com presents a recognised public issuer
[ok  ] http_egress          egress works (https://api.anthropic.com/v1/models returned HTTP 401)

2 passed · 0 warning(s) · 2 failure(s) · 0 could not run

NO-GO — resolve the above first

Two details matter more than the checks themselves. Every finding carries its own fix — a report that just says FAIL: unreachable has pushed the diagnosis back onto the customer, so the code raises if an actionable finding has no remedy. And "could not run" is counted separately from "passed": a check that couldn't execute reports BLOCKED, which outranks FAIL, because a green report that means "we didn't look" gets discovered in the customer's deployment window. The same rule runs through every project below: a gate that cannot fail is not a gate.

How I can help

Focused engagements with clear outcomes and a defined finish line. Scope and day rate — let's discuss on a call.

☸️

Kubernetes & Cloud Platform Build

Production-grade clusters on AKS / GKE / EKS, provisioned as code.

  • Terraform + Helm, multi-environment
  • Ingress, autoscaling (HPA), observability
  • RBAC, network policies, secrets management
🔐

DevSecOps Pipeline Hardening

Shift-left security baked into your delivery pipeline.

  • SAST / SCA / secret & image scanning
  • GitOps with ArgoCD, safe rollouts & rollback
  • Policy-as-code & supply-chain security
🤖

AI Infrastructure & LLMOps

Deploy and secure LLM / agentic-AI workloads at scale.

  • LLM inference serving & RAG on Kubernetes
  • MCP servers & multi-agent automation
  • AI-security guardrails (PII, injection, cost)
🛫

Forward-Deployed / Solutions Engineering

Getting your product live inside a customer environment you don't control.

  • Pre-deployment environment verification
  • Egress, TLS interception & least-privilege RBAC
  • Pilot readiness: model access, rate limits, data residency
🧠

Agent Engineering

Multi-agent systems that do real work and can be trusted with it.

  • LangGraph pipelines with tool use & state
  • Hard cost caps, dry-run modes, audit trails
  • Evaluation harnesses — not vibes
💰

Cloud Cost & FinOps

Find the spend, cut it, then keep it from creeping back.

  • Multi-cloud cost attribution & anomaly alerts
  • Rightsizing, autoscaling & spot strategy
  • 40% reduction delivered in production

Selected work

Open-source, production-style platforms — each with architecture docs, CI, offline tests, and one-command setup. Filter by what you need built.

FLAGSHIP
🛫 Forward-Deployed Preflight
Verifies a customer environment meets your product's prerequisites before you deploy into it — egress, TLS interception, K8s RBAC, LLM provider access. Every finding ships with its fix; a check that can't run reports BLOCKED, never a silent pass.
156 offline testsKubernetesRBACLLMOps
FLAGSHIP
⭐ AI Freelance Copilot
Multi-agent system (LangGraph + Claude + RAG + MCP) that sources leads, scores them against a real ICP, and drafts grounded proposals. Hard per-run spend cap, outcome-first reporting that names the bottleneck stage, and per-source funnel attribution.
363 offline testsLangGraphRAGMCPFastAPI
🛡️ LLM Guardrails Gateway
AI-security gateway in front of any LLM API: prompt-injection detection, PII redaction, output filtering, and token/cost limits.
FastAPIAI SecurityKubernetes
🔌 MCP DevOps Server
Model Context Protocol server exposing Kubernetes, cloud and CI tooling to any AI agent — Claude Desktop, IDEs, or custom agents.
MCPPythonKubernetes
🧠 Agentic SRE Platform
Multi-agent incident response on LangGraph: detect → diagnose → remediate → postmortem, with dry-run safety on every action.
LangGraphClaudeSRE
🤖 AI DevOps Agent
Agent that detects and auto-remediates Kubernetes issues using Claude tool-use plus the K8s Python SDK.
LangChainClaudeKubernetes
⚡ LLM Inference on Kubernetes
Production vLLM serving with Istio traffic management, HPA autoscaling, and Prometheus/Grafana observability.
vLLMIstioHelm
📚 RAG Platform on Kubernetes
Ingestion → embeddings → vector store → grounded generation, with an evaluation harness and Helm deploy.
RAGQdrantFastAPI
☁️ Multi-Cloud K8s (Terraform)
One-command Kubernetes provisioning across AWS EKS, GCP GKE and Azure AKS with Terraform + Helm. Cut infra cost 40% in production.
−40% costTerraformEKS/GKE/AKS
🔐 DevSecOps CI/CD Pipeline
Secure CI/CD with Trivy + Snyk scanning, image build to ECR, and GitOps deploy via ArgoCD. Deploy frequency up 75%.
+75% deploysGitHub ActionsTrivyArgoCD
🔁 GitOps Multi-Environment
Full GitOps across dev/staging/prod with ArgoCD App-of-Apps, Helm and Kustomize overlays.
ArgoCDKustomize
🔑 Keycloak SSO on Kubernetes
Enterprise OIDC single sign-on — Keycloak IdP behind NGINX ingress with oauth2-proxy.
KeycloakOIDCNGINX
💰 Cloud Cost Optimiser
Daily multi-cloud cost reports with anomaly detection → PostgreSQL → Telegram alerts.
FinOpsBoto3Python
🧰 DevOps Automation Toolkit
Practical automation: Kubernetes health checks, database backup, Docker cleanup, log aggregation.
PythonAutomation
→ Everything else
Full repository list on GitHub, including infrastructure modules and smaller utilities.
GitHub

How I work

Four rules I apply to every engagement. They come from production failures, not from a blog post.

A gate that cannot fail is not a gate

Most "monitored" systems fail silently because the check was wired so it could only pass. I verify every guard by planting a violation and watching it fire — before I trust it in production.

Uptime is not a result

A pipeline that exits green on every run while producing nothing is the most expensive kind of broken. I report outcomes, name the bottleneck stage, and make activity metrics secondary.

A wrong report is worse than a missing one

Missing data makes you look. Wrong data makes you act — and debug five healthy components. Diagnostics get the same scrutiny as the code they describe.

Ship in reviewable increments

Small PRs with green CI, tests that state the defect they prevent, and commit messages that explain why. You stay in control of what lands and can hand it to your own team afterwards.

Tech stack

Cloud-native, security, and AI-infrastructure tooling I work with daily.

Cloud & Kubernetes

AzureGoogle CloudAWS (EKS/EC2/S3/RDS) KubernetesAKS / GKE / EKSTerraformHelmDockerIstio

CI/CD & Security

ArgoCDGitHub ActionsJenkinsKustomize TrivySnykSonarQubeOPAKeycloak / OIDC

AI & Agents

LangGraphLangChainClaude / AnthropicMCPvLLMRAGQdrantPrompt-injection defence

Observability & Data

PrometheusGrafanaLokiELK PostgreSQLRedisPythonBashAnsible

Let's build something secure

Tell me what's broken or what you're trying to ship. If I'm not the right person I'll say so on the call rather than after the invoice.

Currently taking on new contract work — London, UK or fully remote