Staff AI Agent Architect — Production-Grade Orchestration

Edisyl; Boston; Hybrid; PHP 350,000 - 520,000; Full time

Job summary

edisyl is building AI solutions that turn messy institutional data into decisions, workflows, and outcomes. We are seeking a Staff-level architect to own the agent ecosystem, including Forge, Lattice, and Stratum, and to ensure production deployments are reliable and auditable.

You will define standards for tool use, memory management, and semantic grounding, aiming for quasi-determinism and high output quality in enterprise contexts.

Qualifications

• 6–10 years building production AI or data systems at scale.
• Deep hands-on experience with multi-agent architectures.
• Strong Python and familiarity with agent frameworks (LangChain, LlamaIndex, AutoGen).

Responsibilities

• Design and build the architecture for AI agent workflows — 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
• Define standards for agent reliability, observability, and failure modes in production deployments
• Collaborate with Forward-Deployed Engineers to translate client environments into reusable platform components
• Build internal tooling and eval harnesses to assess agent quality, hallucination rates, and task completion
• Make principled architectural decisions — stay current with ecosystem and choices to adopt or ignore

Skills

Python

Multi-agent architectures

Production AI

Systems thinking

Client-focused architecture

Tools

LangChain

LlamaIndex

AutoGen

RAG

Vector databases

Job description

edisyl is building AI solutions that turn messy institutional data into decisions, workflows, and outcomes. We are seeking a Staff-level architect to own the agent ecosystem, including Forge, Lattice, and Stratum, and to ensure production deployments are reliable and auditable.

You will define standards for tool use, memory management, and semantic grounding, aiming for quasi-determinism and high output quality in enterprise contexts.