Join our AI Research team to push the boundaries of multi-agent orchestration, agent memory systems, and AI-powered code generation. You'll work directly on the intelligence layer that makes NeuralOS unique.
What You'll Do
- Research and implement novel multi-agent coordination algorithms
- Build and optimize the Agent Memory system (vector search, RAG pipelines)
- Develop prompt engineering frameworks for reliable AI agent behavior
- Design evaluation benchmarks for agent quality, safety, and performance
- Collaborate with Product and Engineering to ship research into production
- Publish findings and represent NeuralOS at AI conferences
What We're Looking For
- MS/PhD in Computer Science, AI/ML, or related field (or equivalent experience)
- 3+ years working with large language models in production
- Strong Python skills and experience with ML frameworks (PyTorch, HuggingFace)
- Deep understanding of RAG architectures, vector databases, and embedding models
- Published research or significant open-source contributions in AI/NLP
- Experience with prompt engineering and LLM evaluation methodologies
Nice to Have
- Experience building AI agents or autonomous systems
- Familiarity with reinforcement learning from human feedback (RLHF)
- Experience with model fine-tuning and distillation
- Background in multi-agent systems or game theory