Multi-agent Software Architectures Researcher - Internship

Siemens is a global technology company focused on industry, infrastructure, transport, and healthcare. They are seeking an innovative PhD intern to support their Software Systems and Processes team by researching and developing scalable intelligent systems using LLMs and semantic technologies.

Responsibilities

• Conduct cutting-edge research into the principles and mechanisms for AI-driven self-organization and dynamic composition within complex software architectures
• Develop and evaluate novel algorithms and frameworks that enable software components to dynamically organize and orchestrate themselves based on stated user needs and objectives
• Design and implement proof-of-concept prototypes to demonstrate the feasibility and effectiveness of dynamic system composition and intelligent component interaction
• Investigate methods and strategies to ensure repeatability and determinism in the outcomes of AI-driven, self-organizing software systems
• Explore and apply advanced AI techniques for interpreting intents, understanding component capabilities, and facilitating intelligent software composition and adaptation
• Collaborate closely with the research team to define project milestones, analyze results, and contribute to the overall research agenda
• Document research findings thoroughly, contribute to scientific publications, and present results at internal and external forums

Skills

• Currently enrolled in a PhD program in Computer Science, Artificial Intelligence, or a closely related technical field
• 1+ year(s) Foundational knowledge and research experience in Artificial Intelligence, Machine Learning and GenAI
• 1+ year(s) Understanding of microservice architectures, cloud-native principles, and distributed computing concepts
• Demonstrated ability to conduct independent research, critically analyze complex problems, and propose innovative solutions
• Experience with fine tuning of LLM (e.g., LoRA) and training/testing ML models
• 1+ year(s) Advanced knowledge of transformer-based models, attention mechanisms, and the latest LLM architectures (e.g., GPT, BERT, encoder-decoder)
• Proficient in Python and ML frameworks (e.g., Pytorch, HF transformers or similar)
• Experience with Vector Databases (e.g., Pinecone, Milvus, Weaviate, Chroma or other)
• Background knowledge in representation and semantic technologies (e.g., RDF, SPARQL, OWL)
• Proficient in English both written and verbal
• The position does require the person to be in the United States of America and hold a valid work permit for the US
• Prior research experience in AI, distributed systems, or autonomous systems, demonstrated through academic publications, thesis work, or significant project contributions
• Hands-on expertise with Large Language Models (LLMs), including fine-tuning, prompt engineering, or integration into system design
• Familiarity with semantic technologies, knowledge graphs, ontology engineering, or symbolic AI
• Aptitude for quickly learning and adopting new technologies and frameworks
• Proficiency with containerization technologies (e.g., Docker, Kubernetes) and major cloud platforms (e.g., Azure, AWS)
• Knowledge of agent-based systems, multi-agent systems, or autonomous systems
• Background in AI Agentic frameworks and platforms (e.g., LangGraph, Semantic Kernel, NeMo)
• The ability to articulate complex technical concepts clearly
• Skill in working with graph databases (e.g., Neo4j, AWS Neptune) and knowledge graph toolsets (e.g., Altair Graph Studio)
• Competence with RAG frameworks
• Capability in deploying and serving LLMs (e.g., vLLM)
• Track record of contributing to research publications, open-source projects, or significant academic projects
• Excellent problem-solving skills and attention to detail
• Capacity to work independently and manage time effectively

Company Overview