Staff Engineer - AI Platform in भारत

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for a Staff Engineer – AI Platform based in India. The Staff Engineer – AI Platform will architect and build advanced AI foundations and agentic systems that empower engineering teams to develop and operate intelligent applications at enterprise scale. This hands-on technical leadership role combines system design, software development, and strategic direction to establish reliable, reusable AI platform capabilities. You will build production-grade AI agents, shared frameworks, model gateways, and evaluation systems while improving developer productivity through intelligent automation. You will also lead efforts to strengthen AI safety, observability, scalability, and cost efficiency across cloud infrastructure. Working closely with product engineering, security, infrastructure, and leadership teams, you will shape technical standards and drive an AI-first engineering culture. This remote opportunity is ideal for an experienced engineer passionate about distributed systems, agent orchestration, and building resilient AI capabilities that deliver measurable impact. Accountabilities: - Architect, develop, and maintain production-grade agentic systems featuring multi-step reasoning workflows, tool usage, orchestration, planning, memory and context management, and human-in-the-loop controls. - Build and evolve a shared AI platform for product and engineering teams, including reusable agent frameworks, tool integrations, Model Context Protocol (MCP) integrations, LLM gateways, and prompt and model versioning. - Design and implement LLM gateway capabilities such as model routing, rate limiting, caching, fallback strategies, and usage controls. - Establish comprehensive AI evaluation and observability practices, including evaluation frameworks, regression testing, agent tracing, and production metrics for quality, latency, cost, and safety.

- Lead the adoption of AI-driven engineering workflows, developer tooling, and automation that improve engineering velocity and reduce repetitive operational work. - Manage cloud infrastructure for AI workloads across Google Cloud Platform (GCP) and/or AWS, including provisioning, scaling, security, access management, and cost governance. - Implement robust AI safety and reliability measures, including guardrails, scoped permissions, sandboxing, prompt-injection defenses, audit trails, graceful degradation, and incident management practices. - Drive continuous optimization of inference, token usage, and infrastructure costs while maintaining high standards of performance, reliability, and output quality. - Define technical architecture and engineering standards, lead design reviews, produce design documentation, and mentor engineers across teams. - Collaborate with product engineering, site reliability engineering, infrastructure, security, and organizational leadership to align AI platform capabilities with business and technical priorities. - Use measurable performance data to guide architectural decisions, prioritize improvements, communicate risks, and report on platform health, agent quality, and cost efficiency. - Champion an AI-first engineering culture, ensuring teams adopt shared AI capabilities and achieve measurable improvements in productivity and operational effectiveness. Requirements: - At least 12 years of overall software engineering experience, including substantial experience as a senior or staff-level individual contributor. - At least one year of recent experience architecting and operating production agentic systems, including multi-step tool-using agents, orchestration, memory and context management, and safety guardrails. - An AI-first mindset, with active use of AI tools in personal engineering workflows and the ability to encourage adoption across an engineering organization.