Lead AI Automation Engineer – Agentic Systems

About the role

We are seeking a Lead AI Automation Engineer to design, build, and deploy autonomous AI systems that transform manual enterprise processes into reliable, orchestrated networks of AI agents. The role requires a deep technical background, a curiosity for cutting‑edge AI models and frameworks, and the ability to turn fast‑moving innovation into production‑grade business solutions.

Key responsibilities

• Design and implement agentic AI architectures that combine large language models, open‑source models, tool use, APIs, retrieval‑augmented generation, memory layers, workflow orchestration, observability, and guardrails.
• Collaborate with business teams to map existing workflows, identify automation opportunities, and translate them into agent roles, prompts, policies, and human‑in‑the‑loop mechanisms.
• Integrate AI agents with enterprise systems such as CRMs, ERPs, ticketing platforms, document management systems, internal databases, communication tools, and custom APIs.
• Develop robust connectors, function‑calling schemas, API contracts, validation layers, retry mechanisms, logging, and monitoring to ensure security, auditability, and compliance.
• Continuously monitor deployed agents, evaluate performance, and iterate to improve reliability and business impact.

Required profile

• Strong software engineering background with experience delivering production‑grade systems.
• Deep familiarity with AI/ML concepts, especially large language models and agentic patterns.
• Proven ability to analyze complex business processes and redesign them as autonomous or semi‑autonomous workflows.
• Comfortable working in ambiguous environments and translating rapid AI research into practical solutions.

Required skills

• Large language models (LLMs) and open‑source model integration
• API integration and function‑calling schemas
• Workflow orchestration and automation frameworks
• Retrieval‑augmented generation and memory layer design
• Observability, logging, and monitoring for AI systems
• Implementation of guardrails and compliance controls