The Role
- Design and build GenAI systems that turn LLMs into composable, dependable tools leveraging retrieval, tool use, agentic reasoning, and structured outputs.
- Design and implement a highly reliable and scalable agent runtime: orchestration, shared state and memory, tool-calling interfaces, and scheduling for cost, latency, and quality.
- Build secure, sandboxed execution for agent actions and code; optimize cold start, isolation, and observability.
- Ship unified interfaces for multiple model sizes and providers; integrate with open tool ecosystems such as MCP-style connectors for data and actions.
- Develop an evaluation platform for online and offline assessments, A/B tests, safety checks, and regression gates that improve agent reliability over time.
- Partner with Research to deliver new agent capabilities end to end—from prototype to production.
What You’ll Bring
- Experience building agent applications with tool-calling, context engineering, or open connector integrations.
- Fluency with LLM APIs, prompting strategies, and orchestration patterns (e.g., LangChain, LlamaIndex, or custom pipelines).
- Experience with retrieval systems (e.g., semantic and lexical retrieval, vector DBs, efficient kNN), function calling, tool use, or agentic workflows.
- Strong coding skills in one or more of: Python, Java, Go. Comfortable with service design, APIs, and data models for high-throughput systems.
- Working knowledge of containers and Kubernetes concepts. Familiarity with metrics, tracing, on-call rotations, and incident response practices.
- Self-motivated with a willingness to take ownership.
- Strong communication skills and ability to work collaboratively in a team environment.
Bonus Points If…
- Prior work on agent orchestration pipelines: task routing, planning, memory graphs, vector search, or browser automation.
- Experience with evaluations, preference optimization, or RL to improve LLM reliability.
