Senior/Staff Software Engineer: Agents

• Own and deliver AI agent experiences end-to-end, including backend orchestration, LLM integrations, conversational interfaces, tool execution, and evaluation systems • Design scalable architectures for agentic AI systems and contribute to platform-level AI infrastructure • Build and improve shared systems such as: • Tool abstractions • Retrieval pipelines / RAG systems • Conversation persistence • Evaluation frameworks • Permissioning and observability • Collaborate closely with Product, Design, and Engineering leadership to define technical direction and product strategy • Make thoughtful engineering tradeoffs balancing latency, reliability, scalability, and cost efficiency • Improve AI system quality through experimentation, evaluation frameworks, and continuous iteration • Lead or contribute to large-scale technical initiatives across multiple teams • Mentor engineers and promote engineering best practices across the organization

• Experience with Retrieval-Augmented Generation (RAG) systems at production scale • Prior experience building customer-facing AI products • Background working at high-growth or venture-backed startups • Contributions to open-source AI tooling, agent frameworks, or developer productivity systems • Experience mentoring engineers or leading technical initiatives • Familiarity with AI observability and evaluation workflows • Experience with cloud infrastructure and modern deployment practices

Position Overview We are seeking a highly experienced Senior/Staff Software Engineer to help design and build next-generation AI-powered agent platforms for customer-facing applications. This role is ideal for engineers who thrive in fast-paced startup environments, enjoy solving complex technical challenges, and have hands-on experience shipping production-grade LLM or agentic AI systems. The ideal candidate brings strong full-stack engineering capabilities with a backend-first mindset, deep familiarity with AI tooling and infrastructure, and the ability to lead high-impact cross-functional initiatives from concept through production. This is a fully remote opportunity open to candidates located in the United States or Canada. Key Responsibilities • Own and deliver AI agent experiences end-to-end, including backend orchestration, LLM integrations, conversational interfaces, tool execution, and evaluation systems • Design scalable architectures for agentic AI systems and contribute to platform-level AI infrastructure • Build and improve shared systems such as: • Tool abstractions • Retrieval pipelines / RAG systems • Conversation persistence • Evaluation frameworks • Permissioning and observability • Collaborate closely with Product, Design, and Engineering leadership to define technical direction and product strategy • Make thoughtful engineering tradeoffs balancing latency, reliability, scalability, and cost efficiency • Improve AI system quality through experimentation, evaluation frameworks, and continuous iteration • Lead or contribute to large-scale technical initiatives across multiple teams • Mentor engineers and promote engineering best practices across the organization Required Qualifications • 5+ years of professional software engineering experience • Proven experience building and shipping production-grade AI/LLM-powered applications or agentic systems • Strong expertise in backend development using Node.js and TypeScript • Experience designing scalable distributed systems, microservices, and backend infrastructure • Hands-on experience with: • Tool calling • Prompt engineering • Agent loops • AI orchestration frameworks • Familiarity with evaluation and observability tooling for non-deterministic AI systems such as: • LangSmith • Braintrust • Custom evaluation frameworks • Full-stack engineering experience with modern frontend frameworks such as React and TypeScript • Strong understanding of databases such as PostgreSQL and MongoDB • Excellent communication and collaboration skills with cross-functional teams • Demonstrated ownership mentality and ability to operate independently in ambiguous environments Preferred Qualifications • Experience with Retrieval-Augmented Generation (RAG) systems at production scale • Prior experience building customer-facing AI products • Background working at high-growth or venture-backed startups • Contributions to open-source AI tooling, agent frameworks, or developer productivity systems • Experience mentoring engineers or leading technical initiatives • Familiarity with AI observability and evaluation workflows • Experience with cloud infrastructure and modern deployment practices Compensation & Benefits • Competitive base salary ($210K – $230K DOE) • Competitive equity package • Fully remote work environment • Opportunity to work on cutting-edge AI products with significant technical ownership • High-impact role within a rapidly growing engineering organization Originally posted on Himalayas AI-Engineering, Backend-Engineering, Fullstack-Development, Agentic-AI-Development, Senior-AI-Agent-Engineer, AI-Agents-Engineer, Senior-Agentic-AI-Engineer, Senior-Agentic-Systems-Developer, AI-Agent-Systems-Engineer, AI-Agent-Platform-Engineer, Senior-AI-Software-Engineer, Software-Engineer