About the Team We are Quadcode, a fintech company excelling in financial brokerage activities and delivering advanced financial products to our global clientele. Our flagship product, an internal trading platform, is offered as a Software-as-a-Service (SaaS) solution to other brokers. We're developing a next-generation IDE for multimodal AI generations and agentic scenarios. It's a full-featured platform that allows users to build complex AI solutions without deep infrastructure knowledge.Quadcode.ai is already available for download: https://quadcode.ai/ Skill Engineer — you are the architect of reusable AI components for the platform. You create ready-made "skills" that other users can embed into their projects. Your task is to develop, optimize, and scale solutions that work reliably and efficiently.This is a role for someone who understands the architecture of AI systems, can optimize prompts across different models, and anticipates edge cases. \n Tasks Develop ready-made skills — reusable components for common AI tasks (text analysis, classification, RAG, agentic workflows, etc.) Optimize prompts across different models and scenarios; conduct A/B testing and measure output quality Design RAG integrations and agentic pipelines — from architecture to implementation Work with integrations — connecting external APIs, vector databases, knowledge sources Test and document skills — create usage examples, handle edge cases, establish best practices Analyze requirements and turn them into scalable components Monitor skill performance and iterate based on feedback Stay on top of AI trends and add new capabilities to the platform

Requirements

Technical education (completed or in progress) — CS, Engineering, Mathematics, Physics, or related field Deep understanding of LLMs — how modern models work, their limitations and strengths; hands-on experience with ChatGPT, Claude, Gemini beyond casual use Prompt engineering experience — not just writing prompts, but optimizing them, A/B testing, understanding how different parameters affect outputs Python development — at a level sufficient for creating integrations, testing, and automation Systematic and architectural thinking — ability to design scalable solutions and anticipate edge cases Analytical approach — ability to measure, compare, and make decisions based on data English B1+ — reading docs, API documentation, research papers Self-sufficiency — doesn't require step-by-step instructions; can navigate unfamiliar systems independentl Nice to have Experience with RAG (Retrieval-Augmented Generation) and vector databases (Pinecone, Weaviate, Milvus) Familiarity with agentic frameworks (AutoGPT, LangChain, LlamaIndex patterns) Fine-tuning experience or working with models through different APIs (OpenAI, Anthropic, Hugging Face) Understanding of function calling and tool use in LLMs Experience with evaluation frameworks for assessing AI output quality Work with semantic search, knowledge graphs Experimentation and metrics monitoring (latency, cost, quality) What we offer Competitive salary and remote work Full-time or part-time, flexible schedule Access to modern AI tools and models (OpenAI API, Anthropic, etc.) Opportunity to influence platform architecture Mentorship and professional growth in a fast-evolving field Professional, positive team \n With a team of 500+ creative and tech-driven people across the globe, Quadcode is the place where ideas turn into impact, where every project is a chance to grow, innovate, and make your mark. Join us today, and let's shape the future of fintech together! Note: All applications will be treated with strict confidence. We thank all applicants for their interest, however, only those candidates selected for interviews will be contacted. With a team of 500+ creative and tech-driven people across the globe, Quadcode is the place where ideas turn into impact, where every project is a chance to grow, innovate, and make your mark. Join us today, and let's shape the future of fintech together! Note: All applications will be treated with strict confidence. We thank all applicants for their interest, however, only those candidates selected for interviews will be contacted. #LI-VS1