Staff Engineer - AI Platform

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.
• Expert-level proficiency in at least one of the following programming languages: Go, Python, or Node.js.
• Strong hands-on engineering experience, including writing and reviewing code, debugging production issues, and making deep architectural contributions. Candidates whose work has been exclusively managerial rather than hands-on during the past year are not a fit for this role.
• Strong understanding of LLM application fundamentals, including tool and function calling, MCP, retrieval, context engineering, prompt and model management, and evaluation methods for nondeterministic systems.
• Extensive experience with observability practices, particularly AI observability, including tracing agent executions and monitoring production quality, latency, cost, and safety. Familiarity with Prometheus, Grafana, ELK/OpenSearch, or equivalent tools is expected.
• Deep knowledge of distributed systems architecture, including consistency, availability, fault tolerance, scalability, and large-scale system design trade-offs.
• Demonstrated experience optimizing costs in enterprise cloud environments, including managing LLM inference and token spend through model routing, caching, and budget controls.
• Practical experience managing GCP and/or AWS services, including infrastructure provisioning, scaling, identity and access management (IAM), networking, and cost governance.
• At least three years of experience as an individual contributor on platform engineering teams operating at enterprise scale.
• Proven ability to lead through technical influence, including writing design documents, aligning cross-functional teams, setting engineering standards, and mentoring other engineers.
• Strong analytical and data-driven decision-making skills, with experience using performance metrics to guide priorities and report outcomes.
• Excellent written and verbal communication skills, with the ability to influence technical and non-technical stakeholders.
• Preferred: Open-source contributions or published work related to agentic systems.

Benefits

• Remote working arrangement in India.
• Professional growth opportunities through technical leadership and ownership of enterprise-scale AI platform initiatives.
• Opportunities to work on advanced AI agents, cloud infrastructure, distributed systems, and developer productivity tooling.
• Collaboration with a globally distributed engineering organization and cross-functional technical teams.
• Opportunity to shape AI engineering standards, mentor engineers, and influence platform architecture and strategy.

How Jobgether Works

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Why Apply Through Jobgether?

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.