AI Network Engineer

We're building software for modern platforms and operating systems, supporting leading networking equipment manufacturers, cloud-native solutions, and infrastructure projects where AI/ML is a core tool for engineering and networking challenges.

• Hands-on experience with LLM-driven workflows, agentic frameworks such as LangChain and LangGraph, and tool-calling patterns
• Experience designing structured tools with clear descriptions, input/output schemas, validation logic, and integration with external APIs or command-based systems
• Experience with semantic search, vector databases, RAG patterns, prompt engineering, and structured LLM outputs
• Experience creating golden queries, automated tests, regression checks, and chatbot/agent response evaluations including LLM-as-a-judge approaches
• Proven experience developing production-quality Python code, including automated tests and maintainable integration logic
• Networking expertise with CCNA certificate or equivalent knowledge, understanding networking platforms, device commands, and troubleshooting
• English at B2 level minimum, preferably C1 or C2

Nice to have:

• Experience with AI-assisted coding tools such as Codex, GitHub Copilot, Cursor
• Familiarity with Model Context Protocol (MCP), MCP server design, tool permissions/scopes, and agent-to-agent communication patterns such as A2A
• Understanding routing agents, supervisor/planner patterns, multi-agent workflows, guardrails, architectures combining deterministic logic with LLM reasoning
• Experience with evaluation frameworks like DeepEval, LangSmith, OpenAI Evals, TruLens, BenchLLM
• Practical AI/ML knowledge for infrastructure data: classification, clustering, anomaly detection, time-series analysis, applied to telemetry, syslog, events, alerts
• Experience deploying AI/LLM solutions in production with Docker, Kubernetes, CI/CD, monitoring, MLOps, or cloud/hybrid infrastructure
• Experience building dashboards, notebooks, or lightweight apps for analysis and validation using tools like Jupyter, Streamlit, Plotly, Altair, matplotlib

• Developing MCP-like tools exposing network device APIs and CLI commands with clear descriptions, structured inputs/outputs, validation, and error handling
• Managing tool metadata and supporting semantic search over available tools using a vector database
• Creating golden user queries and variations for tools, intents, and network-operation scenarios
• Building automated tests to verify tool selection, parameterization, output structure, and agent responses
• Designing evaluation workflows combining deterministic checks, human review, and LLM-as-a-judge techniques using tools like DeepEval
• Refining prompts, tool descriptions, schemas, and agent workflows while monitoring regressions
• Developing production-quality Python code and tests using frameworks such as LangChain and LangGraph
• Collaborating with software engineers, network domain experts, and DevOps teams to deliver reliable, testable, and maintainable agentic workflows