Senior Applied Research Scientist
Core
Design and build the agent execution harness (orchestration layer) enabling AI agents to reason over enterprise data, manage multi-agent workflows, and execute actions reliably at Fortune 500 scale.
Role type
Senior Applied Research Scientist (Agentic AI Infrastructure)
Builds
The agent harness, orchestration runtime, multi-agent coordination systems, and evaluation frameworks for production AI agents.
Domain
Enterprise AI / Agentic Systems / Large Language Model Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Generative AI product ownership, LLM failure modes and context constraints, prompt engineering and versioning, eval engineering, distributed systems, API design, testing discipline, cost/latency tradeoff analysis.
Preferred skills
Multi-agent coordination patterns (A2A, MCP), agent frameworks (LangChain, LlamaIndex), AI observability tooling, cloud-native infrastructure.
Technologies
LLMs, LangChain, LlamaIndex, distributed systems, API design.
Responsibilities
Design and build the agent execution harness; own runtime fault tolerance, latency, and throughput; instrument the harness with tracing and cost attribution; build prompt management systems; design evaluation frameworks; integrate and abstract over frontier LLMs; define system boundaries for agent logic.
Seniority
Senior, hands-on IC with technical leadership
