Senior AI Platform Engineer

Overview

Senior AI Platform Engineer on the AI Platform team, which builds the foundational capabilities (LLM gateway, developer tooling, coding agents, inline guardrails, evaluation frameworks, retrieval, and platform services) that let engineering and product teams develop, deploy, and operate AI-powered experiences. This is a hands-on platform engineering role, not a model-training or research role.

What you'll do

• Own an AI platform deliverable from problem definition through production launch, adoption, and ongoing operation.
• Design, build, and operate platform capabilities such as LLM gateways, retrieval systems, agents, developer tooling, evaluation frameworks, and inline guardrails.
• Define success criteria and measurable outcomes before building, then use production data and baseline metrics to guide future improvements.
• Design systems with clear SLOs, strong observability, predictable failure handling, and reliable operational processes.
• Develop and maintain clean interfaces, migration paths, documentation, and paved paths that make platform adoption simple for engineering teams.
• Build retrieval and agent systems with a clear separation between retrieval quality and answer quality, supported by meaningful evaluation strategies.
• Design for secure and controlled AI execution, including least-privilege access, multi-tenant isolation, permissioning, auditability, and operational boundaries.
• Apply strong distributed systems principles, including consistency, idempotency, concurrency, resilience, rollout strategies, and failure-mode analysis.
• Use coding agents and other AI development tools effectively while validating their output through testing, review, and sound engineering judgment.
• Carry operational ownership for the systems you build, including participation in an on-call rotation, incident response, and post-incident improvement.
• Partner closely with Engineering, Product, Security, Infrastructure, SRE, and Developer Experience teams to ensure platform capabilities are practical, scalable, and widely adopted.
• Establish and communicate reusable technical patterns, standards, and reference implementations for building production-ready AI systems.

What you'll need

• Demonstrated experience building or operating production retrieval systems, agent platforms, AI tooling, or other AI-enabled capabilities that real users depend on.
• Strong software engineering experience designing and operating distributed systems within an existing architecture.
• The ability to identify and clearly reason about consistency, idempotency, concurrency, failure modes, multi-tenant isolation, security, and rollout risks.
• Practical understanding of AI system quality, including retrieval evaluation, answer quality, release gates, agent reliability, and cost per request.
• Experience designing systems with clear success criteria, measurable baselines, observability, and operational targets such as SLOs.
• Strong understanding of secure AI execution patterns, including least-privilege access, permissioning, auditability, and policy enforcement.
• Experience taking a platform or product capability from problem definition to production and remaining accountable for its reliability, adoption, and continued improvement.
• Ability to work effectively with coding agents and AI development tools, while independently verifying generated code and recommendations.
• A strong production mindset, including experience with incident response, on-call operations, monitoring, debugging, and post-incident learning.
• Excellent communication and collaboration skills, with the ability to make complex technical concepts accessible to engineering and product stakeholders.
• A customer-focused mindset: understanding that a platform capability teams do not adopt is not a successful outcome.
• A One Team orientation and a willingness to create reusable capabilities that enable other engineering teams to move faster and more safely.

Nice to have

• Experience with LLM gateways, agent frameworks, retrieval-augmented generation, evaluation systems, or AI developer platforms.
• Experience with FinOps, cost optimization, or usage-based measurement for AI systems.
• Experience in application security, policy enforcement, identity, access management, or secure platform design.
• Experience with search quality, ranking, experimentation, or relevance evaluation.
• Experience with OpenTelemetry, distributed tracing, AI observability, or production telemetry.
• Experience building multi-tenant infrastructure or internal developer platforms.
• Experience with developer advocacy, technical enablement, SDKs, documentation, or helping teams adopt new engineering capabilities.
• Familiarity with routing systems, API gateways, service orchestration, workflow engines, or platform control planes.

Details

• Location: Hyderabad, Telangana, India.
• Works from the local Hyderabad office 2-3 times a week (hybrid).
• On-call rotation participation is required.