Senior AI DevOps / Platform Engineer (AI Agents & MCP)
Convo · Islamabad
Job description
About the role
Convo is looking for a Senior AI DevOps / Platform Engineer to build, scale and maintain production delivery platforms and infrastructure for AI Agents, LLM workflows and Model Context Protocol (MCP) servers. The role establishes repeatable evaluation gates, enforces sandboxed agent execution, enables zero-downtime rollouts and ensures high availability for non-deterministic AI workloads.
Key responsibilities
- Deploy, host, scale and operationalise AI Agent frameworks, vector stores and MCP servers across Kubernetes clusters.
- Design CI/CD pipelines for Python services, agent definitions, prompts, tools, MCP servers and platform configuration.
- Implement GitOps-based Kubernetes deployments with promotion, rollback and environment-specific policies.
- Integrate automated unit, API, security and LLM-evaluation checks (prompt stability, tool-use accuracy, output safety, latency/cost regression) into release gates.
- Implement secrets handling, dynamic sandbox isolation for agent execution and least-privilege deployment identities.
- Instrument pipelines and services for agent-level observability (token usage, tool invocation, LLM latency, cost, distributed tracing), health monitoring and incident diagnosis.
- Maintain reusable deployment templates and coach engineering teams on release standards.
Required profile
- 9+ years in DevOps, SRE or platform engineering, including 3+ years with production Kubernetes, GitOps and infrastructure as code.
- Hands-on experience deploying AI Agents, LLM infrastructure or MCP servers, and scaling AI-driven solutions, vector databases, proxy gateways or MCP servers in production.
- Strong CI/CD and GitOps experience for Kubernetes-hosted services.
- Preferred: canary, blue/green and progressive delivery; LLM/agent evaluation frameworks (DeepEval, Ragas, LangSmith); software supply-chain controls, artifact signing and dependency scanning.
Required skills
- Terraform or equivalent infrastructure as code, preferably on Azure.
- Python scripting for pipelines, release checks and operational automation.
- Secrets management, container security, workload isolation and dynamic agent sandboxing.
- Monitoring, alerting and telemetry (LangFuse, Phoenix/Arize, OpenTelemetry, Datadog, Prometheus).
- Experience enforcing automated test and LLM evaluation results in CI.
What we offer
- Great compensation package and medical benefits for you and your family.
- Free lunch, annual performance-tied increments and performance recognition awards.
- A lean and agile work culture, with Convo endorsing diversity.
Questions fréquentes
Why are you reporting this job?
Explore further
Salaries, guides and searches in Pakistan.
Salaries by job title
Apply in 30 seconds
Enter your email to apply. An account will be created automatically.
By continuing, you accept our terms of use.
Already have an account? Login
A question about this job?
Ask it here: you will get the full job summary by e-mail, right away.
Published 1 week ago
Expires 1 month from now
22 views · 0 interested
Boost your chances
Upload your CV — we will match you with relevant openings.
Analyzing your CV...
Convo
Islamabad