AI Agent Architect (Staff) — AI Agents / LLM Systems

edisyl builds AI systems that transform large-scale, unstructured institutional data into usable workflows and decisions. Originating from blockchain data infrastructure across 20+ chains, the team now applies this capability to enterprise environments where reliability, auditability, and scale are critical.

This role operates in a remote, full-time setup, working on production-grade AI systems using Python, LLM APIs, and multi-agent architectures. The position focuses on designing systems that perform consistently across real-world enterprise data conditions, including regulated environments.

You will define and own the architecture behind agent reliability, orchestration, and semantic grounding across core internal systems. This includes building infrastructure that ensures consistent outputs beyond prompt-based approaches — a key requirement in blockchain infrastructure roles and enterprise AI deployments.

🔹 Responsibilities

• Design and implement architectures for AI agent workflows, including planning loops, tool usage, memory systems, retrieval, and human-in-the-loop checkpoints
• Evaluate, integrate, and fine-tune foundation models and LLM APIs for enterprise-specific data use cases
• Establish standards for reliability, observability, and failure handling in production agent systems
• Collaborate with forward-deployed engineers to convert client-specific solutions into reusable platform components
• Build internal tooling and evaluation frameworks to measure agent performance, hallucination rates, and task completion
• Make and document architectural decisions while staying current with evolving AI and agent ecosystem developments

🔹 Requirements

• 6–10 years of experience building production-grade AI or data systems operating reliably at scale
• Hands-on experience with multi-agent architectures, including context handling, memory systems, and dependency structures
• Strong Python expertise and familiarity with frameworks such as LangChain, LlamaIndex, AutoGen, or equivalent systems
• Practical experience with retrieval-augmented generation (RAG), vector databases, and context window optimization
• Experience deploying LLM-powered systems in enterprise environments with security, access control, and audit requirements

Additional Capabilities

• Strong understanding of LLM failure modes and limitations beyond prompt engineering
• Demonstrated production judgment in shipping and maintaining reliable systems
• Clear architectural perspective on scaling agent systems in enterprise contexts
• Systems-level thinking with focus on failure modes and resilience

Bonus (Optional)

• Exposure to ML research areas such as fine-tuning, RLHF, or model evaluation
• Experience in regulated industries (financial services, insurance, healthcare)
• Familiarity with blockchain data infrastructure or institutional crypto systems

🔹 Compensation & Benefit

• Competitive base salary (exact figures not specified)
• Early-stage equity participation
• Full-time employment structure

Looking to build a web3 engineering team or hire for roles like this?
Explore talent pipelines and hiring support at →Home | ArtofBlockchain