Staff Software Engineer AI

About the Role

• Would you like to set the technical direction for an AI and agent platform used by thousands of brands? We’re looking for a Software Engineer, Platform (AI) to join the AI team of a U.S.-based social media management software company, whose platform includes publishing, reporting, customer care, influencer marketing, and proprietary agentic AI.
• You’ll own the reliability, scalability, and architecture of the AI and Agent platforms end to end. You’ll set the build, ship, and monitoring practices that other teams adopt, and you’ll work with product managers, designers, and applied AI/ML scientists to bring generative AI and agentic features to production. You’ll also mentor engineers and act as the go-to person for difficult architectural decisions.

About You

• You’re an experienced, impact-oriented engineer who enjoys working on cutting-edge, fast-changing technology.
• You think carefully about secure system design and want to accelerate the delivery of generative AI and agentic AI features.
• You build with AI in your own work, using tools such as Claude Code, and set the example for others.
• You enjoy researching and prototyping emerging AI technologies and turning them into practical technical bets.
• You communicate clearly with product managers, designers, and scientists, and you act as a thought partner, not just an implementer.
• You enjoy mentoring and sharing knowledge across engineering teams.

What You’ll Be Doing

• Own the reliability, scalability, and architecture of the AI and Agent platforms end to end.
• Set the technical direction and the build, ship, and monitoring practices that other teams adopt.
• Build with AI and agentic AI in your daily work, using tools such as Claude Code, to set the example for the team.
• Research and prototype emerging AI technologies, frameworks, and state-of-the-art methods, and help prioritize technical bets by effort, risk, and impact.
• Partner with product managers, designers, and applied AI/ML scientists, within and across the AI domain.
• Write design documents and RFCs that other teams build against, and coordinate dependencies across teams.
• Drive improvements in scalability, reliability, latency, and cost of AI systems.
• Mentor engineers, share knowledge across the R&D organization, and serve as an escalation point for ambiguous and complex architectural decisions.

What We’re Looking For

• Technical ownership and the ability to set direction without waiting for instructions.
• Strong judgment when balancing effort, risk, and impact.
• Clear written and verbal communication across technical and non-technical teams.
• A mentoring mindset and a commitment to raising the engineering bar.
• Curiosity and comfort with rapidly changing technology.

Technical Requirements

Must-Haves

• 5+ years designing, developing, and supporting production-grade backend distributed systems or platform services at scale, in languages such as Java or Python.
• 5+ years improving architectural patterns of large-scale software applications.
• 3+ years driving root-cause analysis and resolving complex architectural and performance bottlenecks across the stack.
• 3+ years architecting high-throughput, cost-optimized, scalable systems that power AI-enabled features.
• 1+ years implementing LLM and agent orchestration frameworks (for example, LangChain4j, LangGraph, or CrewAI).
• Experience designing and implementing secure, extensible MCP (Model Context Protocol) architectures.
• Advanced English.

Nice-to-Haves

• Experience supporting server-driven UI, with the ability to contribute across both platform and web.