Reinforcement Learning Specialist
SpaceXAI
Building Grok at SpaceXAI — reinforcement learning environments, LLM post-training tooling, and Model Context Protocol (MCP) infrastructure for AI systems.
- Reinforcement learning environments for model training loops
- LLM post-training tooling and evaluation pipelines
- MCP and AI systems that bridge research and product
Company

SpaceXAI
Building Grok
- Focus
- RL environments · LLM post-training · MCP · AI systems
- Since
- January 2026 · India
- Previously
- Landeed (YC) · Purpose Digital · REO
“RL environments, LLM tooling & MCP.”






