Resources by role — AI Platform Engineer
AI Platform Engineer
This is an individual contributor role on the AI & Cloud Operations Team. You will own the platform underpinning the DevOps practice (AKS, CI/CD, IaC, and operational excellence) while equally driving AI development pipeline strategy, MCP server infrastructure, and the modernization of the company's delivery toolchain and developing AI Agents using various AI platforms such as Claude, Gemini, Sierra, and DevRev. This is a hands-on role with DevOps experience, cloud knowledge, and previous AI Agent development and deployment.
What this role does
Key responsibilities
Production Readiness Assessment
- Receive prototype applications and conduct structured assessments covering posture, data model integrity, authentication and authorization flows, input validation, dependency hygiene, and test coverage quality
- Identify and document failure patterns endemic to AI-generated code including hardcoded secrets, flat or unindexed schemas, missing error handling, and hallucinated or unpinned dependencies
- Produce clear remediation plans with prioritized findings working within the architectural standards set by the Full-Stack Systems Architect
- Hands on experience building Agentic agents in Gemini/Vertex, OpenAI, Claude, or similar tools
Code Remediation & Hardening
- Refactor and harden AI-generated codebases to meet enterprise production standards across frontend frameworks, backend APIs, data modeling, and authentication systems
- Replace or rewrite AI-generated test suites against human-reviewed acceptance criteria, ensuring coverage reflects real production behavior rather than checkbox validation
- Use AI-augmented development tools (Cursor, Claude Code, GitHub Copilot) to accelerate remediation work while exercising independent judgement on when AI tooling is introducing new risk
Security and Compliance
- Identify and remediate common security vulnerabilities including injection flaws, broken authentication, insecure direct object references, and exposed secrets or credentials
- Implement and validate secure authentication and authorization patterns in accordance with enterprise security policies
- Ensure applications meet CI/CD pipeline requirements and version control standards prior to production deployment
Pattern Recognition & Knowledge Management
- Document recurring AI code failure patterns and contribute to a growing internal knowledge base
- Feed pattern intelligence back upstream to improve prototype quality at the source, collaborating with developers and architects to reduce remediation burden over time
- Stay current on AI-assisted development tooling, emerging failure modes, and production readiness best practices
Collaboration & Communication
- Partner with application teams, architects, and business stakeholders to align on readiness criteria and timelines
- Communicate technical findings clearly to both engineering and non-technical audiences
- Provide guidance and thought leadership on responsible use of AI development tools within the engineering organization
What this role requires
Required qualifications
Core Engineering
- Strong full-stack fundamentals across at least one major frontend framework (React, Vue, Angular), backend API development, relational data modeling, and authentication systems
- Proficiency in Python, JavaScript/TypeScript, and at least one additional backend language
- Solid understanding of RESTful API design, database schema design, and ORM patterns
- Experience with version control discipline, branching strategies, and code review processes
AI Code Failure Pattern Recognition
- Strong ability to identify AI-generated code failure modes: hardcoded credentials, hallucinated libraries, flat schemas, checkbox tests, missing error handling, and over-reliance on happy-path logic
- Practical experience evaluating AI tool output for correctness, security, and production viability
- Ability to distinguish between AI tooling as an accelerant versus AI tooling compounding a problem
Security & Production Standards
- Familiarity with OWASP Top 10 and common application security vulnerabilities
- Experience implementing or validating secure authentication flows (OAuth 2.0, JWT, session management)
- Understanding of CI/CD pipeline requirements, environment configuration, and secrets management
Testing & Quality
- Experience writing and reviewing test suites with meaningful coverage: unit, integration, and end-to-end
- Ability to evaluate test quality and replace AI-generated checkbox tests with coverage that reflects real production behavior
Communication & Collaboration
- Strong written and verbal communication skills with the ability to present technical findings to non-technical stakeholders
- Proven ability to work both independently and with cross-functional engineering teams
- Self-starter with strong problem-solving skills and a bias toward documentation and knowledge sharing
Nice to have
Preferred qualifications
- Hands-on experience building MCP servers or LLM tool-use integrations
- Hands-on experience building agentic agents in Gemini/Vertex, OpenAI, Claude, or other AI tools
- Expertise in CI/CD pipelines
- Experience with Kong, Kuma, or compatible API/service mesh tooling
- Exposure to AI-assisted development platforms (Lovable, Cursor, Claude Code)
- Experience with monitoring and observability platforms (Dynatrace)
Background
Education & Experience
- Bachelor's degree in Computer Science, Information Systems, or a related field; equivalent professional experience considered
- 5+ years of full-stack software development experience
- 3+ years of hands-on experience with AI-augmented development tools in a professional context (Cursor, Claude Code, GitHub Copilot, or equivalent)
- 2+ years of experience in application security, code review, or production engineering disciplines
- Demonstrated experience identifying and remediating vulnerabilities in production codebases
Working style
How you'll work
You'll collaborate daily with platform engineers, application developers, and security and compliance stakeholders. You will operate with a high degree of autonomy, be expected to drive decisions, document your work, and bring others along. You will have access to the best in class AI-forward tooling and will be expected to model and advance that culture.
Ready to go deeper?