Senior Platform Engineer

Responsibilities

• 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 incident triage, deployment validation, configuration remediation, and capacity planning.
• Drive AI-assisted code review and developer tooling using tool-use, validation steps, and human-in-the-loop gates.
• Operationalize LLM-based features with structured prompting, RAG, output validation, and evaluation harnesses.
• Implement LLM gateway and router patterns to control costs, route models, and provide observability for AI workloads.
• Design and evolve GitOps-based continuous delivery and Kubernetes infrastructure on AWS EKS.
• Manage infrastructure as code with Terraform, Helm, and Kustomize.
• Strengthen observability, reliability, and operational excellence through SLOs, error budgets, metrics, traces, logs, and automation that improves MTTD and MTTR.
• Extend the developer control plane with paved paths, scorecards, and self-service actions.
• Instrument platform cost signals, including compute, observability, and AI/LLM spend, and build FinOps automation.
• Define success metrics and run time-bound experiments evaluating developer efficiency, reliability, and cost.
• Document usage guidance, patterns, and best practices for proven AI workflows.

Requirements

• Bachelor's or master's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• 4+ years of platform, infrastructure, or backend engineering experience operating production systems in a cloud environment; AWS preferred.
• Strong Python and/or Go coding skills with experience building and operating production services.
• Deep experience with Kubernetes, preferably EKS; GitOps with Argo CD; CI/CD with GitHub Actions; and Terraform, Helm, and Kustomize.
• Experience with service mesh technologies.
• Strong observability skills with Datadog APM, metrics, tracing, and logs, plus a record of improving reliability and promoting SLO/error-budget practices.
• Hands-on experience building or integrating MCP servers, including tool-surface design, scope and authorization management, and connecting AI agents to infrastructure.
• Production experience with structured or agentic AI workflows, including planning/execution separation, human-in-the-loop validation, RAG, and tool-use patterns.
• FinOps experience covering cloud cost attribution, workload optimization, and AI/LLM spend control.
• Familiarity with LLM gateway and router patterns for cost control, model routing, and AI workload observability.
• Clear communication and effective collaboration with distributed partner teams.
• Experience using AI-assisted development tools such as GitHub Copilot, Cursor, or ChatGPT.

Benefits

• Healthcare coverage.
• Internet and cell phone reimbursement.
• Learning and development stipend.
• Potential opportunities to travel to the Mountain View headquarters.
• Hybrid work based in the Bengaluru office, with two days on-site.
• Visa sponsorship and immigration support are not available.