Sr Specialist System Engineering (GenAI Engineer – Network Automation & RCA)

Job Responsibilities 

• Design, develop, and deploy applied ML solutions for anomaly detection, forecasting/prediction, and RCA using large‑scale operational data (logs, KPIs, traces, and test outputs).  

• Engineer end‑to‑end GenAI capabilities including RAG pipelines (retrieval, chunking, embeddings, ranking, grounding) to provide accurate, source‑aligned answers and insights.  

• Build agentic AI workflows using multi‑agent orchestration (planner/orchestrator + specialized agents) to execute complex troubleshooting tasks and decision support.  

• Implement tool‑calling/skills frameworks (MCP‑style patterns) so agents can securely invoke internal APIs, query data stores, and perform controlled actions.  

• Develop automated triage workflows that correlate signals across data sources, identify likely root causes, and propose remediation steps with clear confidence/justification.  

• Apply telecommunications domain knowledge (4G/5G Core procedures, IMS services, and network function behaviors) to interpret anomalies, validate hypotheses, and improve RCA precision.  

• Implement guardrails for agentic systems: safe tool access, input/output validation, prompt‑injection defenses, and human‑in‑the‑loop approvals for impactful actions. 

• Create evaluation and quality mechanisms for AI outputs (offline test sets, regression prompts, expected outputs, and measurable accuracy/latency standards).  

• Productionize services with strong engineering discipline: API design, error handling, retries, performance tuning, logging/metrics, and operational runbooks. 

• Partner with platform, DevOps, security, and product teams to integrate AI capabilities into existing workflows and user experiences. 

• Drive continuous improvement through telemetry and feedback loops (usage metrics, response quality, failure analysis, and iterative model/prompt/agent refinement).  

Job Qualifications / Required Qualifications 

• Strong hands‑on Python engineering experience building production services (APIs, backend services, and automation).  

• Solid applied ML foundation with proven experience delivering anomaly detection, prediction/forecasting, classification, clustering, or RCA‑oriented analytics.  

• Experience working with large‑scale operational/telemetry data (log/event data, time‑series KPIs, traces) and designing features/signals for models 

• Hands‑on experience implementing GenAI workflows, including RAG (retrieval strategies, embeddings, grounding, and response quality techniques).  

• Experience building agentic workflows (multi‑step reasoning, tool calling, orchestrated agents, state management, and robust failure handling).  

• Telecommunications domain knowledge with understanding of 4G EPC and 5G Core networks, including IMS services and end‑to‑end call flow concepts (e.g., VoLTE/VoNR/IMS registration and data session flows).  

• Understanding of evaluation methods for ML/LLM systems (accuracy, false positives/negatives, robustness, latency, and cost trade‑offs).  

• Strong software engineering practices: clean code, testing, version control, and ability to troubleshoot complex systems.   

• Ability to communicate clearly and work effectively with distributed on‑shore/off‑shore teams.  

• Hands-on experience with agentic coding tools and workflows, including Claude Code and GitHub Copilot. 

Preferred Qualifications 

• Practical familiarity with 4G/5G Core network functions and interfaces (e.g., AMF/SMF/UPF/PCF/MME/HSS/UDM and IMS signaling concepts) and how failures manifest in logs/KPIs.  

• Experience with deep learning or neural networks (helpful but not required), especially for sequence/time‑series modeling or representation learning. 

• Familiarity with multi‑agent orchestration frameworks (e.g., graph‑based orchestration, agent routers, and tool registries).  

• Experience with vector databases / semantic search stacks and optimization techniques (reranking, hybrid retrieval, caching strategies).  

• Experience deploying ML/GenAI services on cloud or hybrid platforms; familiarity with containers and orchestration (Docker/Kubernetes). 

• Experience with MLOps practices (model/version management, monitoring, drift detection, CI/CD for ML, and reproducible pipelines). 

Additional Job Information 

This is an offshore role that requires daily collaboration with U.S. stakeholders, including overlapping work hours to ensure effective partnership and meet business needs.