Staff Engineer – AI Platform

This is a fully remote position, open to applicants in India.

📋 Description

• Design and construct production-ready agentic systems for automating platform operations and enhancing internal engineering processes.

• Create a unified AI platform featuring reusable agent frameworks, integrations for tools and MCP, an LLM gateway, as well as versioning for prompts/models.

• Implement evaluation and observability measures for AI systems, which include evaluation harnesses, agent-run tracing, and metrics related to quality, latency, cost, and safety.

• Propel AI-assisted developer workflows and automate operational tasks.

• Oversee GCP/AWS cloud infrastructure dedicated to AI workloads, focusing on provisioning, scaling, security, and cost management.

• Take ownership of and advance a reliable, extensible, and high-performance architecture for agentic systems.

• Set up guardrails, define scoped permissions, implement sandboxing, establish defenses against prompt injection, maintain audit trails, ensure graceful degradation, and develop incident management practices.

• Develop offline evaluations, regression testing suites, and production monitoring systems.

• Optimize costs related to inference, tokens, and infrastructure.

• Establish technical standards, conduct design reviews, mentor engineering staff, and advocate for excellence in AI engineering practices.

• Collaborate with product engineering, SRE/infrastructure, security, and leadership teams.

• Articulate technical direction, identify risks, and report progress throughout the organization.

⛳️ Requirements

• 12+ years of comprehensive software engineering experience, including substantial time as a senior or staff-level individual contributor.

• Minimum of 1 year spent architecting agentic systems in a production environment.

• Proficient in designing multi-step, tool-utilizing agents, orchestration, context management, and guardrails.

• AI-first mindset with active engagement in utilizing AI tools within engineering workflows.

• Expert-level skills in Go, Python, or Node.js.

• Strong experience in hands-on coding, code review, production debugging, and system architecture.

• Solid understanding of tool/function calling, MCP, retrieval and context engineering, as well as prompt/model management and evaluation strategies.

• Extensive AI observability experience with tools like Prometheus, Grafana, ELK/OpenSearch, or the equivalent.

• Strong grasp of distributed systems architecture principles.

• Proven track record of measurable cost optimization within an enterprise cloud environment.

• Practical experience managing services in GCP and/or AWS, including provisioning, scaling, IAM, networking, and cost governance.

• At least 3 years of experience as an individual contributor on platform teams at an enterprise scale.

• Capability to lead technically without formal authority, produce design documents, facilitate cross-team collaboration, and mentor fellow engineers.

• Data-driven mindset for decision-making, prioritization, and performance reporting.

• Exceptional verbal and written communication abilities.

• Contributions to open-source projects or published work related to agentic systems are advantageous.

🏝️ Benefits

• Global organization with a remote-first culture.

• Chance to engage in AI-driven projects at an enterprise scale.

• Opportunities for technical mentorship and leadership development.

• Contributions to open-source projects or published work on agentic systems are viewed favorably.