Associate Engineer (AI-Focused) - Cayuse

Join our remote-first culture as an Associate Engineer, an entry-level, hands-on engineering role focused on building AI capabilities directly into Cayuse products. You will work alongside senior engineers to design, build, test, and ship AI agents, Model Context Protocol (MCP) servers, and LLM-powered features that help research institutions and their administrators work faster and with less manual effort. This is not a data science or ML research role. It is a software engineering role for someone early in their career who writes solid code, learns quickly, and wants to grow into a strong AI engineer by shipping real features to real customers.

Responsibilities

• AI Agent Development: Build and maintain AI agents that use large language models (such as Claude) to complete multi-step tasks within Cayuse products — calling tools, retrieving data, and taking actions on behalf of users. Implement prompts, tool definitions, and orchestration logic under the guidance of senior engineers.
• MCP Server Development: Help build and extend Model Context Protocol (MCP) servers that allow AI assistants to securely interact with Cayuse products. Work with senior engineers to implement tools, APIs, authentication, and permission checks using established engineering standards. Write clear documentation and tests to ensure these integrations are reliable and reusable.
• Hybrid AI Validation: Help turn AI-extracted rules, such as requirements parsed from funding opportunity instructions, into deterministic, auditable validations that run alongside existing form rules and are reviewed by people before use.
• Product Integration: Integrate AI features into existing Cayuse applications through platform APIs. Build on the shared capabilities and patterns set by the architecture team instead of one-off implementations, and partner with product teams so AI fits naturally into customer workflows.
• Testing & Evaluation: Write unit and integration tests for AI features, and help build evaluation sets that measure the accuracy, reliability, latency, and cost of LLM outputs. Contribute to time-boxed AI pilots and help document whether each should go, pivot, or stop. Investigate failures, identify root causes, and propose fixes.
• Deployment & Operations: Ship code through CI/CD pipelines to cloud environments (AWS, including Amazon Bedrock). Add logging and monitoring to AI services and help troubleshoot production issues.
• Learning & Collaboration: Participate in code reviews, design discussions, and sprint ceremonies. Keep current with the fast-moving AI tooling ecosystem and share what you learn with the team.
• Governed AI Platform: Develop AI features using Cayuse’s shared AI platform and established engineering standards. Learn how our platform handles model access, security, tenant isolation, usage tracking, and auditing. Work with senior engineers to ensure new features follow these patterns rather than introducing one-off solutions.
• Responsible AI & Security: Follow established security and privacy standards when developing AI features. Learn to recognize and test for risks such as prompt injection, unauthorized data access, and inaccurate AI outputs. Work with senior engineers to ensure AI features respect user permissions, protect customer data, and maintain proper tenant isolation. Raise potential security or reliability concerns early.

Qualifications

Core Experience

• 0–2 years of professional software development experience, including internships, co-ops, or apprenticeships.
• Demonstrated ability to build working software through coursework, internships, personal projects, open-source contributions, or hackathons. A portfolio or GitHub profile is strongly encouraged.
• Exposure to team-based development using version control (Git), code review, and agile practices.
• BS in Computer Science, Software Engineering, or a related field, or equivalent practical experience.

Technical Skills

• Software Development: Proficient in at least one general-purpose language (Python or TypeScript/JavaScript preferred; Java with Spring Boot also valued). Solid grasp of data structures, APIs, error handling, and writing tests.
• AI & LLM Fundamentals: Demonstrated interest in AI technologies and how they can be applied to software development. Experience experimenting with LLM APIs, prompt engineering, tool calling, or retrieval-augmented generation (RAG) through coursework or personal projects is a plus. A willingness to learn and understand how these technologies work is more important than prior experience with any specific AI framework.
• Agents & MCP: Familiarity with the Model Context Protocol, agent frameworks, or AI coding assistants (such as Claude Code or GitHub Copilot).
• APIs & Integration: Working understanding of REST APIs, JSON, and authentication basics (API keys, OAuth).
• Cloud & Infrastructure: Exposure to a cloud platform (AWS preferred; Amazon Bedrock a plus), containers (Docker), or CI/CD pipelines is a plus.
• Data Fluency: Comfortable writing basic SQL queries and working with structured data. Exposure to Snowflake or another cloud data warehouse is a plus.

Collaboration & Communication

• Clear communicator — writes readable code, documentation, and pull request descriptions, and raises questions early when blocked.
• Strong problem-solving instincts: you break ambiguous tasks into smaller steps and work through them methodically.
• Coachable and growth-oriented — you seek out feedback and apply it.
• Collaborative and adaptable — effective in a remote-first environment and when coordinating across offshore, nearshore, and onshore teams.
• Genuine curiosity about how AI is changing software and knowledge work, paired with practical judgment about where it adds real value.