AI Architect

Role Overview
Job Summary (AI Architect Remote)
Lead the design, development, and scaling of production AI agent systems.
Own core components: agent harness, evaluation framework, guardrails, and routing layer with built-in security.
Collaborate with product, platform, security, and risk teams to transition AI agents from prototype to production.
Key Responsibilities
Design and implement agentic harnesses, including agent loops, tool/function calling, planning, memory, multi-agent orchestration, and human-in-the-loop workflows.
Develop and maintain evaluation frameworks (offline/online) for measuring task success, accuracy, groundedness, cost, and latency; integrate into CI/CD pipelines.
Implement guardrails for safety, prompt-injection/jailbreak defense, PII redaction, and tool-level permissions.
Build intelligent routing across LLMs, agents, and tools for optimized intent, complexity, cost, latency, and risk handling.
Apply AI security best practices: threat modeling (OWASP Top 10, MITRE ATLAS), least-privilege access, secrets management, sandboxing, and audit logging.
Deploy, operate, and monitor agents in production environments with full observability and tracing.
Mentor engineering team members and define standards for agent development.
Required Qualifications
Bachelor s or Master s in Computer Science, Engineering, or related field, or equivalent experience.
5+ years in software engineering (2+ years with LLM/agentic applications in production).
Hands-on experience in building agent harnesses, evaluation frameworks, guardrails, and model routing.
Familiarity with agent frameworks (e.g., LangGraph, OpenAI Agents SDK, Claude Agent SDK, CrewAI, AutoGen, MCP).
Experience with evaluation and guardrail tools (e.g., LangSmith, Langfuse, Braintrust, promptfoo, NeMo Guardrails, Guardrails AI).
Strong security skills: threat modeling, IAM, secure API design, data protection.
Proficient in Python; experience with RAG, vector databases, Docker/Kubernetes, and cloud platforms (AWS, Azure, GCP).
Excellent communication skills for explaining AI risks to non-technical stakeholders.
Preferred Qualifications
Experience in banking, financial services, or regulated industries (KYC/AML, fraud detection, customer service, operations).
Familiarity with AI governance/model risk frameworks (SR 11-7, EU AI Act, NIST AI RMF, ISO/IEC 42001).
Knowledge of compliance standards: PCI DSS, SOC 2, ISO 27001.
Security or cloud certifications (CISSP, OSCP, AWS/Azure/GCP).

Work arrangement
Yes