AI Engineer (Fullstack)

TL;DR

AI Engineer (Fullstack): Building and optimizing an AI-powered content generation system across LangGraph orchestration, React frontend, and Supabase backend with an accent on autonomous research, quality evaluation, and adaptive output formatting for different platforms. Focus on designing and implementing LangGraph agents, building research pipelines, and debugging complex multistep agent interactions.

Location: Fully remote (UTC to UTC+6 timezone preferred)

Company

AlumniHub is building an AI-powered content generation system that autonomously researches, structures, and generates publication-ready content across any niche and platform.

What you will do

• Design and implement LangGraph agents and workflows.
• Build research pipelines that extract entities and relations from web data.
• Improve content quality through evaluation metrics and feedback loops.
• Build adapters for different output formats (articles, social posts, product pages) and platforms.
• Work on streaming, real-time updates, and frontend integration.
• Debug complex multistep agent interactions.

Requirements

• Strong Python with async/await, experience building production systems.
• Can own features across the stack when needed (backend to frontend).
• Learns new frameworks quickly.

Nice to have

• LangChain/LangGraph or similar agent frameworks experience.
• Background in distributed systems, message queues, or workflow engines.
• React + TypeScript experience.
• Experience debugging non-deterministic systems.
• Worked with LLM APIs in production (token management, cost optimisation, error handling).

Culture & Benefits

• Fully remote work with minimal meetings.
• High autonomy and ownership.
• Focus on shipping fast and iterating based on real results.
• Emphasis on clean, readable code.