Senior AI Platform / System Engineer - Coding Agents and MCP

About the role

Pixalate is hiring a Senior AI Platform / System Engineer in Lahore to turn product-specific AI coding agents, currently running on individual laptops, into shared agents that run in the cloud. You will package each product's agent once, host it for every engineer, keep its knowledge current as code changes, and provide secure, measured access. You will also own the production infrastructure on AWS and GCP, including monitoring, patching, backups, CI/CD, releases and cloud costs. The role works with engineering leads in the US, Singapore and Pakistan, uses Claude via managed APIs and does not cover model training, data science or GPU serving.

Key responsibilities

• Package each product's coding agent as a versioned plugin (skills, subagents, CLAUDE.md context and MCP configuration) and host it on GCP and AWS using the Claude Agent SDK and headless Claude Code in containers (Cloud Run, ECS), triggered from Bitbucket Pipelines, Jira and Slack.
• Keep agents accurate by indexing code and documentation from Bitbucket repos and the docs site, refreshing it on every merge and running evaluation suites per codebase, starting with MRT.
• Build and run shared MCP servers for Bitbucket, Jira, read-only BigQuery and AWS, with per-user authentication, short-lived credentials, least-privilege access and audit logs.
• Route model traffic through the Claude API, Amazon Bedrock or Google Vertex AI with budgets and cost caps, track usage and cost per engineer and agent, and support adoption with documentation and onboarding.
• Operate production on AWS and GCP, configure and tune services, own monitoring and alerting (CloudWatch, Google Cloud Monitoring, logging stack), and investigate and fix production issues.
• Take production on-call during business hours, with an escalation contact for incidents outside them.
• Keep systems patched and recoverable, with OS and software upgrades, kernel and security patching, backups and disaster recovery with tested restores.
• Own CI/CD on Bitbucket Pipelines and the release process, manage infrastructure as code and configuration management (Terraform, Ansible), and track and reduce cloud spend with budgets and reporting.
• Maintain security hygiene: IAM reviews, secrets management and access cleanup.

Required profile

• Bachelor's degree in Computer Science, Software Engineering or a related field.
• 6+ years in DevOps, SRE or platform engineering, running production systems on AWS or GCP, including monitoring, patching and backups and disaster recovery.
• Hands-on experience deploying AI coding agents (Claude Code or similar) for a team, with shared context, skills, subagents or plugins and agents run automatically from CI or a server; you will walk through one.
• Strong Linux administration, networking fundamentals and production troubleshooting.
• Secrets management and least-privilege IAM on AWS or GCP.
• Excellent written and verbal English, assessed with a written exercise; comfortable working across time zones with overlap with US business hours.
• Nice to have: international university degree, production experience with the Claude Agent SDK or headless Claude Code, built or hosted MCP servers, Amazon Bedrock or Google Vertex AI, both AWS and GCP, BigQuery administration, OpenTelemetry, evaluation harnesses, sandboxed agent execution, TypeScript, and some exposure to open-weight models.

Required skills

• Containers, infrastructure as code and configuration management (Docker, Terraform, Ansible or similar)
• CI/CD pipelines
• Python scripting and shell
• AWS and GCP
• Bitbucket Pipelines or GitLab CI