Senior AI Platform Engineer

About the Role Senior AI Platform Engineer at EarnIn to design, build, and operate AI-assisted capabilities within platform-owned infrastructure and developer tooling. This role splits time between standard platform engineering and AI engineering, with a focus on shipping production-grade AI-assisted workflows inside existing systems. The position is hybrid and based in Bengaluru, working with Kubernetes, CI/CD, GitOps, observability, FinOps, and infrastructure-as-code to empower reliable, scalable tooling for engineers. What You'll Do

• design and build MCP servers that expose platform capabilities as safe, well-scoped tools for AI agents and developer-facing assistants.
• Contribute to enterprise MCP patterns, LLM tooling, agentic guardrails, knowledge repositories, and framework rollout.
• design structured, agentic workflows for platform operations — incident triage, deployment validation, config remediation, capacity planning — and drive AI-assisted code review and developer tooling (e.g., CodeRabbit, Claude/Cursor) with tool-use, validation steps, and human-in-the-loop gates.
• operationalize LLM-based features inside platform tooling: structured prompting, RAG, output validation, and evaluation harnesses.
• implement LLM gateway and router patterns to control costs, route models, and enable observability of AI workloads.
• design and evolve GitOps-based continuous delivery, Kubernetes infrastructure on AWS EKS, and infrastructure-as-code with Terraform, Helm, and Kustomize.
• strengthen observability, reliability, and operational excellence: SLOs, error budgets, metrics/traces/logs, and automation that improves MTTD/MTTR.
• extend the developer control plane with paved paths, scorecards, and self-service actions.
• instrument platform cost signals — compute, observability, and AI/LLM spend — and build FinOps automation that surfaces waste and supports cost-aware engineering decisions.
• define success metrics upfront and run time-bound experiments to evaluate impact on developer efficiency, reliability, and cost.
• document usage guidance, patterns, and best practices to support consistent adoption of proven AI workflows. What We're Looking For
• Bachelor's or Master's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• 4+ years in platform, infrastructure, or backend engineering with hands-on experience operating production systems in a cloud environment (AWS preferred).
• Strong coding skills in Python and/or Go, with experience building and operating production services.
• Deep experience with Kubernetes (EKS preferred), GitOps (Argo CD), CI/CD (GitHub Actions), and Terraform/Helm/Kustomize for infrastructure automation, service mesh.
• Solid observability skills (Datadog APM/metrics/tracing/logs) with a track record of improving reliability and driving SLO/error-budget culture.
• Hands-on experience building or integrating MCP servers — designing tool surfaces, managing scope and auth, and connecting AI agents to real infrastructure.
• Practical experience with structured or agentic AI workflows (planning/execution separation, human-in-the-loop validation, RAG, tool-use patterns) used in production environments.
• FinOps experience: cloud cost attribution, workload optimization, and AI/LLM spend control.
• Familiarity with LLM gateway/router patterns for cost control, model routing, and observability of AI workloads.
• Clear communication skills and the ability to collaborate effectively with partner teams in a distributed environment.
• Experience using AI-assisted development tools (e.g., GitHub Copilot, Cursor, ChatGPT, or similar tools) as part of your software development workflow. Compensation & Benefits
• EarnIn provides excellent benefits for our employees, including healthcare, internet/cell phone reimbursement, a learning and development stipend, and potential opportunities to travel to our Mountain View HQ.