AI Automation & Agent Engineer (Early Career)

AI Automation & Agent Engineer (Early Career) Remote | Early-stage SaaS | Long-term role Location: Remote (India preferred; some overlap with North America) Type: Full-time, long-term Experience: 0–2 years or strong fresh graduate Compensation: $8,000 – $15,000 USD + equity About the Company We’re an early-stage SaaS startup building tools that help teams review, collaborate on, and manage complex documents and digital assets. Our customers span engineering, design, construction, and content-heavy teams. We’re now exploring AI-powered workflows and standalone agents to improve how reviews, documentation, and approvals happen - with the intent to integrate the best ideas into our core product over time. This role works closely with the founder and plays a direct part in experimentation, evaluation, and early product validation. About the Role This is a builder + experimenter role for someone early in their career who wants hands-on exposure to AI, automation, and real product problems. You’ll help: Build automation workflows Prototype standalone AI agents Evaluate how well AI performs in real review scenarios Turn experiments into clear insights for product decisions Your focus is on systems, agents, and evaluation. What You’ll Work On • AI Automation (Documentation, Marketing, Ops) Build automation workflows using n8n / APIs / webhooks Connect systems like GitHub, Confluence, Figma, support tools, CRMs, and internal trackers Use AI (LLMs) to generate structured outputs (JSON, summaries, analyses) Automate internal processes across documentation, marketing ops, and reporting • Standalone AI Agent Prototyping You’ll help prototype small, focused AI agents such as: Documentation gap detection agents Review summarization agents QA or review-readiness agents Marketing asset review agents These agents will initially live outside the core product as experiments. • AI Review Agent Evaluation (Key Responsibility) You’ll play a critical role in evaluating AI review agents, including: Designing test cases using real-world review data Running agents against sample inputs (documents, comments, feedback) Comparing AI outputs to human reviews Identifying: Where AI performs well Where it fails or hallucinates What guardrails or workflows are needed Documenting findings clearly so product decisions can be made This evaluation work directly informs what gets built into the product later. • Systems & Experimentation Write lightweight Python scripts or services when needed Iterate quickly: test → learn → refine Document experiments and findings for future reuse Work closely with the founder to decide what to pursue vs. drop What We’re Looking For We care more about curiosity, learning ability, and systems thinking than formal experience. You’re a good fit if you: Are comfortable with basic programming concepts (Python, JS, APIs, JSON) Enjoy experimenting and testing ideas Are curious about how AI behaves in real-world scenarios Like solving messy problems with structured thinking Want long-term growth in a startup environment Nice to have (not required): Experience with automation tools (n8n, Zapier, Make) Interest in AI evaluation, QA, or tooling Familiarity with SaaS products or workflows Why This Role You’ll work directly with the founder You’ll help shape how AI is used in a real product You’ll gain rare experience in AI evaluation and product discovery You’ll build systems that actually get used You’ll have room to grow into a senior or specialist role over time Flexible working hours Strong mentorship and learning opportunities How to Apply Please include: A short note on why this role excites you Any projects, experiments, or systems you’ve worked on (academic or personal is fine) One example of something you tried to build or test, even if it didn’t work