Senior Software Engineer, Network Operational Intelligence

Role Overview

Core Responsibilities

• Build automation and orchestration workflows for network provisioning, configuration, monitoring, and assurance.
• Develop agentic AI solutions using LLMs, orchestration frameworks, and vector stores.
• Build scalable tools for network inventory, monitoring, telemetry collection, event correlation, and intent-based management.
• Use GenAI for alert summarization, root cause inference, change impact prediction, and knowledge extraction.
• Design structured prompts, chains, and RAG workflows for context-aware insights from network data.
• Collaborate with product owners, network SMEs, and engineers to identify AI opportunities.
• Own network tooling services across telemetry, topology, configuration management, and orchestration.
• Build natural-language interfaces for operations querying, diagnostics, and root cause analysis.
• Publish high-performance APIs for the network operations ecosystem.
• Mentor engineers and support architecture, delivery planning, performance, and reliability initiatives.

Software Engineering Requirements

• At least 8 years of experience as a Senior Software Engineer or in comparable software engineering work.
• Advanced Python proficiency and experience with AI or NLP libraries such as LangChain, LangGraph, Transformers, OpenAI SDK, HuggingFace, or LlamaIndex.
• Hands-on experience with FastAPI, Flask, or Django for backend services.
• Experience designing secure, high-performance RESTful APIs and authentication or integration patterns.
• Experience with relational databases, ORM frameworks, microservices, Docker, and CI/CD pipelines.
• Experience with TDD, PyTest or unittest, code quality, maintainability, and reproducibility.

AI Engineering Requirements

• Hands-on experience building applications with foundation models such as OpenAI, Claude, LLaMA, Mistral, or Gemini.
• Experience designing autonomous or semi-autonomous agents with reasoning, tool calling, planning, memory, and state management.
• Experience with prompt engineering, embeddings, vector stores, hybrid search, chunking, and reranking.
• Experience evaluating and observing LLM systems, including regression testing, tracing, hallucination mitigation, and fallback mechanisms.
• Familiarity with fine-tuning approaches, structured outputs, secure tool integration, and model serving or inference infrastructure.
• Knowledge of AI security and governance, including privacy, prompt-injection defenses, guardrails, access control, and auditability.

Added Advantage

• Experience in network operations, network automation, observability, or infrastructure monitoring.
• Experience with Kafka, Prometheus, Elasticsearch, or OpenSearch for time-series or telemetry data.
• Exposure to Kubernetes for microservices and AI workload orchestration.

Candidate Qualities