Agentic AI Engineer - Internship

Company Overview:

Nile is reimagining access networking by delivering it as a service — simplifying operations and raising the bar on network security and reliability. We offer a full-stack, cloud-managed solution that spans wired switching, secure access, and policy-driven automation.

The Role:

This role focuses on designing, building, and scaling production-grade agentic AI systems, including multi-step reasoning workflows, tool-integrated agents, and RAG-enabled architectures, while ensuring reliability, performance, and safety. It requires end-to-end ownership of agent systems—from architecture and orchestration to monitoring, evaluation, and failure handling—along with close collaboration on APIs, memory design, and developer tooling. The ideal candidate is a strong software engineer with experience in distributed systems and hands-on deployment of agent-based AI in real-world environments, with deep understanding of LLM behavior, system trade-offs, and production constraints.

Responsibilities:

• Design and Ship Agentic AI Systems: Build and deploy production-grade agents with multi-step reasoning, tool usage, and stateful workflows aligned to real-world use cases such as productivity improvement, business intelligence, etc..

• Implement Agent Workflows End-to-End: Implement full agent lifecycle and orchestration, including RAG integration, ensuring reliability, observability, and performance in production.

• Operationalize Reliability, Evaluation, and Safety: Develop observability, evaluation, and guardrail systems to improve agent quality, robustness, latency, and cost efficiency.

• Deep Technical Collaboration: Partner with engineering on agent architecture, memory systems, and developer-facing APIs/SDKs.

Qualifications:

• Core Engineering Background: 1-3 years building distributed/cloud systems with strong coding skills (Python, Go, Java, or C++).

• Agentic AI Implementation: Hands-on experience designing and deploying production agent systems with orchestration, tool integration, and RAG capabilities.

• Technical Depth: Deep understanding of LLM behavior, memory architectures, retrieval systems, and system design trade-offs.

• Excellent Communication Skills: Effective collaboration across global teams with strong technical communication and clarity in system design.