Research Engineer – Agent Systems & AI Coding Environment (seed Infra Platform)

ByteDance ByteDance · Big Tech · Seattle, WA · R&D

Research Engineer focused on building agent systems and AI coding environments, including distributed training, RL frameworks, and inference infrastructure. The role involves developing agent harnesses, orchestration frameworks, evaluation systems, and productionizing agent systems.

What you'd actually do

  1. Build agent harness and execution environments for AI coding and knowledge tasks (code execution, tool integration, sandboxing, system interaction)
  2. Develop scalable orchestration frameworks for multi-step agent workflows (planning, tool use, memory, coordination)
  3. Design evaluation and benchmarking systems to measure agent performance across complex, long-horizon tasks
  4. Improve agent performance via prompting, data curation, and post-training in collaboration with model and RL teams
  5. Partner with research and product teams to productionize agent systems

Skills

Required

  • Python
  • system-building experience
  • LLM-based systems
  • pipelines
  • tool-integrated workflows
  • system design
  • scalable infrastructure
  • agent harness / runtime systems
  • AI coding environments
  • Docker
  • Kubernetes
  • orchestration systems
  • distributed job execution
  • containerized/sandboxed code execution environments

Nice to have

  • evaluation frameworks
  • prompting
  • finetuning
  • RL
  • large-scale experimentation

What the JD emphasized

  • Experience building agent harness / runtime systems or AI coding environments

Other signals

  • agent systems
  • AI coding environment
  • distributed training
  • reinforcement learning
  • high-performance inference