Applied Research Engineer / Research Intern
Core
Building always-on AI coworkers for the enterprise using multi-agent systems with governed memory and real-time inference.
Role type
Applied Research Engineer / Research Intern
Builds
Multi-agent orchestration systems, governed agent memory, real-time inference pipelines, and evaluation harnesses.
Domain
Enterprise AI, Multi-agent systems, LLMs
Deliverable
production ML models
Required skills
Python, PyTorch, JAX, Hugging Face Transformers, research reproducibility, prototype development, multi-agent orchestration, agent memory management, real-time inference optimization, tool use and API integration, benchmarking and evaluation
Preferred skills
LLM agent frameworks, retrieval systems, vector databases, inference optimization (quantization, KV-cache), distributed systems, edge deployment, enterprise security constraints (SOC 2, RBAC), open-source maintainership, startup experience
