AI/ML Architect

Role Overview We are seeking a Senior Agentic AI Architect who has already designed and deployed AI agent systems in production environments. This role focuses on building autonomous or semi-autonomous AI agents that can reason, plan, use tools, and interact safely with external systems. The successful candidate will design agent reasoning loops, memory systems, tool integrations, and escalation paths while ensuring these systems operate reliably in real operational environments. This role requires someone who understands not only how to build agents, but also the practical pitfalls of operating them in production. Core Responsibilities Agent Architecture Design and implement production AI agents capable of executing complex workflows. Responsibilities include: Designing reasoning loops for planning, tool selection, and self-correction Building multi-agent orchestration systems Implementing memory systems including short-term context and vector memory Defining escalation paths to human operators when needed Implementing guardrails to ensure safe and predictable agent behaviour. LLM and Agent Systems Engineering Build robust LLM-driven systems that integrate with business workflows. Responsibilities include: Building production RAG pipelines using vector databases Implementing structured outputs and function calling Designing context management strategies for complex tasks Integrating agents with external APIs and business systems Applying prompt and context engineering techniques to improve reliability Production Deployment Ensure that agent systems operate safely and reliably in production. Responsibilities include: Deploying agents used by real users and operational teams Implementing monitoring and logging for agent behaviour Managing token usage and LLM cost efficiency Diagnosing hallucinations, tool failures, and workflow breakdowns Implementing fallback and escalation mechanisms when agents encounter Uncertainty. Production Experience (Critical Requirement) Candidates must have real production experience deploying AI agent systems. This includes experience with: Multi-step agent reasoning loops Safe tool use and external system integration Human-in-the-loop escalation workflows Monitoring and reliability of LLM systems Guardrails to mitigate hallucinations and unsafe outputs Managing cost and performance of LLM-based systems Candidates who have only experimented with agent frameworks or built prototypes without deploying production systems will not be considered a strong fit. Essential Qualifications Candidates should demonstrate: 7+ years software engineering experience 2+ years working with LLM or agent-based systems in production Strong Python backend development skills Experience with frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or similar Experience building RAG pipelines and working with vector databases Experience integrating AI systems with APIs and external services Education: Bachelor s or master s degree in computer science, Artificial Intelligence, Software Engineering, or equivalent practical experience.

Full Name

Email

Phone Number (optional)

Years of Experience (optional)

LinkedIn Profile (optional)

Portfolio / GitHub (optional)

Resume / CV (PDF or Word, max 4MB)

Cover Letter / Message (optional)