AI Software Engineer (LLMs, LangChain, Cloud AI) (вакансія неактивна)

Join a leading global technology company that is revolutionizing the way educators, librarians, and institutions worldwide. The platform supports millions of educators and learners across thousands of institutions worldwide, powering real-time AI discovery, personalization, and intelligent search.

As an AI Software Engineer, you will be a key contributor to the development of cutting-edge AI-driven products that impact millions of users across diverse educational environments.

You will work with a talented team of engineers and data scientists to design and implement intelligent systems powered by state-of-the-art Large Language Models (LLMs), advanced AI agents, and scalable cloud infrastructures. Your expertise will help drive the next generation of AI capabilities — from real-time data processing and advanced natural language understanding to AI integration across complex product ecosystems.

Key Responsibilities

• Design and implement AI-powered capabilities using state-of-the-art LLMs, with orchestration via LangChain and LangGraph
• Collaborate on building multi-turn AI agents, tools, and retriever-based pipelines to power features like intelligent search and resource discovery
• Implement cloud-based AI solutions using AWS Bedrock, OpenAI, and Azure AI services (AML, AKS)
• Contribute to prompt engineering, tool design, context retrieval, and model fine-tuning for production-grade LLM applications
• Own and evolve key pieces of AI infrastructure: chaining logic, async workflows, memory management, and API orchestration
• Work closely with product and platform teams to embed AI into core user workflows (e.g., DestinyAI)
• Contribute to internal AI frameworks and toolkits for broader reuse across engineering teams
• Mentor teammates on LLM tooling, prompt strategies, and best practices in cloud-native AI development

Required Qualifications

• 5+ years of software development experience with a strong focus on AI/ML systems or intelligent applications
• Proficient in Python, including asyncio, orchestration logic, and API design
• Hands-on experience with LangChain and LangGraph: chains, tools, memory, agents, retrievers
• Experience working with LLM APIs (e.g., OpenAI, Bedrock, Azure OpenAI), and designing effective prompts
• Understanding of Retrieval-Augmented Generation (RAG) and Model Context Protocol (MCP) concepts
• Familiarity with MLflow or similar tools for experiment tracking and model lifecycle management
• Comfortable developing in notebook environments, debugging pipelines, and visualizing model outputs
• Strong knowledge of API development, integration, and orchestration of multi-step workflows
• Strong communication skills and ability to mentor others in emerging AI technologies

Preferred Qualifications

• Experience with stateful agent workflows (e.g., conditional logic, retries, decision branching using LangGraph)
• Experience debugging multi-turn agent behavior and token usage optimization
• Familiarity with vector search tools or retrieval strategies (e.g., FAISS, Pinecone, Weaviate)
• Experience integrating AI components into production applications (UI and backend)
• Understanding of embedding models, token management, and LLM performance tuning

Why Join Us?

• Build meaningful AI features that improve education for millions of students and educators
• Work with a passionate team building cutting-edge products with real-world impact
• Lead innovation in how AI augments learning, discovery, and digital experiences
• Flexible remote work, collaborative culture, and a mission-driven environment
• Paid vacation, holidays, and sick leaves