Senior Software Engineer

Overview

THE ROLE:
Senior Software Engineer Britebound is a national nonprofit that is changing the way kids learn about careers and prepare for their futures through access to career-readiness information and experiences. We are seeking an AI-experienced Senior Software Engineer to contribute to the design, development, and maintenance of AI-driven applications to augment internal processes and to contribute features to Britebound’s direct-to-consumer web platforms.

This role focuses on building scalable, secure, and user-friendly applications, data transformation, and systems integrations. You will work with product managers, designers, engineers, and data analysts to apply your software engineering and AI-domain experience across the full technology stack to deliver impactful digital solutions.

This role is ideal for someone who enjoys hands-on coding, problem-solving, and collaborating in a cross-functional environment while continuing to grow their technical expertise on a tightly integrated team of technologists.

• Core Engineering
• Develop, test, and maintain cloud applications using modern frontend (React, Type Script) frameworks
• Design and implement AI-driven solutions deployed as cloud applications or services using Python or Azure frameworks and platforms
• Design and articulate technical solutions that deliver cross-cutting value across business goals
• Contribute to the design and implementation of databases (SQL, No
  
  SQL) in Snowflake data warehouses and cloud-based solutions (AWS, Azure, or equivalent)

• AI & LLM-Focused Responsibilities
• Design, build, and deploy LLM-powered features, including chatbots, AI agents and AI assistants that support learners and internal teams
• Integrate and orchestrate LLM APIs from providers such as OpenAI, Anthropic, and Google Gemini, selecting models and approaches appropriate to cost, latency, and accuracy requirements
• Implement retrieval-augmented generation (RAG) pipelines using vector databases and embeddings to ground LLM responses in trusted, domain-specific content
• Develop prompting strategies, system prompts, and evaluation techniques to improve response quality, safety, and reliability
• Collaborate with product, design, and data teams to define human-centered conversational UX patterns and guardrails appropriate for educational contexts
• Monitor, test, and iterate on LLM applications using logging, analytics, and automated evaluation frameworks
• Address privacy, security, bias, and content safety considerations when deploying AI-driven features, especially in environments involving minors or sensitive educational data

• Leadership & Collaboration
• Review and guide the work of other engineers, ensuring adherence to best practices, maintainability, and performance standards
• Act as a technical mentor—supporting the growth and effectiveness of mid-level and junior engineers
• Stay up-to-date with emerging AI technologies and propose pragmatic, mission-aligned applications

• Technical Requirements:
• Core Engineering
• 6+ years of professional experience in full-stack software development
• Demonstrated expertise with modern frontend frameworks (React, Material UI, or similar) and backend development (Node.js, Express, APIs)
• Strong understanding of software architecture, system design, and cloud infrastructure
• Proficiency with CI/CD, containerization (Docker, Kubernetes), and version control (Git)
• Experience working with cloud services such as AWS, Azure, or Firebase (Preference for Azure)
• AI & LLM Experience
• Hands-on experience building production LLM-based applications, such as chatbots, assistants, or AI-enhanced workflows
• Familiarity with LLM orchestration frameworks, tooling, and prototyping techniques (strong preference for Lang Chain)
• Experience working with embeddings, vector databases, and semantic search (e.g., Chromadb, pgvector, or equivalents)
• Understanding of prompt engineering, structured outputs, function/tool calling, and model evaluation techniques
• Experience designing systems that manage latency, cost controls, rate limits, and fallback strategies across multiple model providers
• Awareness of AI ethics, safety, and compliance considerations, especially in…