Position Overview
We are looking for an experienced AI Software Engineer to design and deliver advanced AI-powered capabilities that will transform how millions of users interact with learning and resource platforms. You will work at the intersection of large language models, real-time data systems, and modern cloud architectures: building intelligent agents, Retrieval-Augmented Generation (RAG) pipelines, and event-driven solutions that make education smarter, faster, and more personalized.
About the Project
Our platform processes vast amounts of educational and resource data, integrating modern AI frameworks, LLM orchestration tools, and cloud-native services. The focus is on embedding AI capabilities: from intelligent search to real-time recommendations — directly into core products, powered by AWS Bedrock, Azure ML, LangGraph, LangChain, and scalable event-driven pipelines (Kafka, Spark).
Your Role
- Design and implement AI features using large language models (LLMs), orchestrated with LangGraph and LangChain
- Build and integrate real-time data pipelines and event-driven architectures (Kafka, Spark) to support AI and analytics workloads
- Embed AI capabilities into core products — from intelligent agents to resource discovery and advanced search
- Develop secure, scalable cloud-based solutions leveraging AWS Bedrock, Azure SQL, AML, AKS, and other AI/ML services
- Drive prompt engineering, model fine-tuning, and RAG strategies for improved accuracy and relevance
- Mentor engineers, promote best practices in AI system design, and contribute to internal AI frameworks and toolkits
What We Expect
- 5+ years in software development, with strong AI/ML systems or data-intensive application experience
- Expert-level Python skills for AI pipelines, orchestration logic, and API integrations
- Deep cloud knowledge (AWS required; Azure a plus)
- Solid data engineering experience with ETL/ELT workflows, PySpark/Spark, and large-scale data transformations
- Proficiency in SQL, data modeling, and optimization
- Hands-on experience with LangGraph, LangChain, and Retrieval-Augmented Generation (RAG)
- Familiarity with LLM APIs, SDKs, and prompt engineering best practices
- Strong skills in async/event-driven programming (asyncio) and multi-step workflow orchestration
- Experience with MLflow for model tracking and lifecycle management
- Excellent communication and mentoring abilities
Nice to Have:
- Graph-based thinking for stateful AI agent workflows
- Debugging skills for complex multi-turn, branching agent behavior
- Experience integrating AI into customer-facing applications and backend services
What We Offer
- Fully remote work
- Direct impact on high-visibility AI projects in the education technology sector
- Collaboration with a mission-driven, global team of experts
- Professional growth through training, certifications, and cutting-edge projects
- Paid vacation, public holidays, and sick leave