3 months ago
Remote, Worldwide or Boston, MA, USAStaff+
Responsibilities
- Design and build AI agent workflow architecture covering planning loops, tool use, memory, retrieval, and human-in-the-loop checkpoints.
- Evaluate, integrate, and fine-tune foundation models and LLM APIs for enterprise use cases and data types.
- Define production standards for agent reliability, observability, and failure modes.
- Collaborate with Forward-Deployed Engineers to turn client-environment learnings into reusable platform components.
- Build internal tooling and evaluation harnesses for agent quality, hallucination rates, and task completion.
- Make principled, documented architectural decisions and establish standards for production agent systems.
- Improve Forge, Lattice, or Stratum so they support reliable production deployments.
Requirements
- 6–10 years building production AI or data systems that run reliably at scale under real conditions.
- Deep hands-on experience with multi-agent architectures, including context windows, memory management, and dependency graphs.
- Strong Python skills and familiarity with agent frameworks such as LangChain, LlamaIndex, or AutoGen, or a documented rationale for building an alternative.
- Practical production experience with RAG architectures, vector databases, and context-window management.
- Experience deploying LLM-powered systems in enterprise contexts involving data security, access controls, and audit logging.
- Ability to reason about LLM failure modes, production reliability, agent design, and system failure modes.
- Preferred but not required: ML research exposure, production AI deployments in regulated industries, or familiarity with blockchain data infrastructure and institutional crypto.