About the role
As an Infrastructure Engineer, a typical day involves supporting the definition of requirements and contributing to the design and construction of data center technology components. The role includes active participation in testing activities to ensure the reliability and performance of infrastructure solutions. This position requires close collaboration with various teams to align technology implementations with organizational goals, while continuously monitoring and improving data center operations to maintain optimal functionality and efficiency.
Responsibilities:
- Assist in defining requirements, designing and building data center technology components, and testing efforts.
- Design and build scalable agentic AI platforms supporting multi-step autonomous agents.
- Architect and implement Model Context Protocol (MCP) servers and client ecosystems.
- Develop agent adaptors for multiple LLMs, tools, and AI frameworks.
- Build Agent APIs (REST + gRPC) for lifecycle, streaming, and orchestration.
- Implement multi-agent execution patterns like ReAct and Plan-and-Execute.
- Enable memory, tool-calling, and context persistence for AI agents.
- Ensure security, observability, and reliability of agent workflows.
- Collaborate with ML, product, and platform teams on agentic system evolution.
Requirements:
- 5+ years of software engineering with 2+ years in AI/LLM systems.
- Strong programming skills in Python and TypeScript / Node.js .
- Hands-on experience building production LLM or agentic systems.
- Solid understanding of LLM fundamentals (tokens, context, tools, prompts).
- Experience with API design (REST, gRPC, and Protocol Buffers).
- Familiarity with agent frameworks (LangChain, LlamaIndex, AutoGen, etc. ).
- Experience with distributed systems and cloud platforms.
- Degree in computer science or equivalent practical experience.
Must-have skills:
- Deep experience with agentic AI systems and autonomous workflows.
- Strong knowledge of Model Context Protocol (MCP) or similar standards.
- Expertise in LLM tool-calling, function execution, and orchestration.
- Experience implementing multi-step reasoning agents.
- Practical knowledge of vector databases and agent memory.
- Ability to design guardrails, safety checks, and cost controls for AI agents.
- Experience with real-time streaming and multi-turn agent interactions.
- Proven ability to move AI research concepts into production platforms.
Additional Information:
- The candidate should have a minimum of 7.5 years of experience in automation architecture.
- A 15-year full-time education is required.