AI/ML Engineer – OSS Automation

**Position Summary** We are looking for an **AI/ML Engineer** with 6 years of experience in **telecom OSS/network** operations environments, who has built or is building applied **AI/LLM-based automation** on top of that domain expertise. This role is grounded in deep telecom OSS knowledge first, with agentic AI as the applied layer on top, not the other way around. The role focuses on automating and augmenting OSS workflows such as network assurance, service fulfillment, and configuration management, using LLM-based agents for tasks like alarm triage, RCA, and guided remediation, always within policy-aware guardrails. **What You'll Work On** - **Design and implement LLM** **-based agents** for OSS tasks: alarm triage, incident summarization, RCA, remediation suggestions - **Build closed-loop automation solutions** integrating sensing, decision-making, and execution across OSS components - **Integrate agents with OSS/NMS systems**: fault management, performance management, configuration management, inventory - Consume and reason over **network telemetry** (KPIs, logs, traces), alarms, topology, and service models - **Build RAG pipelines** using operational data, runbooks, policies, and standards (e.g., 3GPP, TM Forum) - **Design agent tooling and action interfaces** to safely execute network changes (config updates, parameter tuning, workflow triggers) - Apply **ML techniques** (anomaly detection, forecasting, classification) alongside LLM reasoning for proactive assurance - **Implement guardrails**, approvals, and rollback strategies for safe automation - **Build evaluation and monitoring frameworks** to measure agent accuracy and operational impact - **Deploy AI automation services** in cloud-native, event-driven architectures ### Requirements - **6 years of experience**in telecom OSS domains, with solid hands-on knowledge of: - Fault, Performance, Configuration, and Service Management **(FCAPS)** - **Network assurance** and service assurance - **Closed-loop** or intent-driven automation concepts - **Strong Python skills** and experience building production-grade automation systems - **Practical, demonstrable experience with LLM-based systems**(this can be more recent than the OSS experience, given how young these frameworks are): - At least **one agent framework** (LangChain, LangGraph, AutoGen, CrewAI, or similar) - **Tool/function calling** and structured outputs - **RAG architectures** using vector databases - Experience working with **network telemetry, alarms, and events** - Familiarity with **REST APIs, TM Forum Open APIs**, or vendor-specific OSS interfaces - Knowledge of **event-driven and streaming architectures** (e.g., Kafka, Pub/Sub) - Experience deploying solutions in **cloud** or hybrid environments - Strong **engineering discipline** (testing, CI/CD, observability) **Nice to Have** - Experience with **5G/LTE OSS**, including RAN, transport, or core network domains - Knowledge of **AIOps** platforms and operational analytics - Experience with time-series analysis and large-scale **KPI processing** - Familiarity with **runbook automation**, ITSM integration, or ticketing systems - Experience with **policy engines** or intent-based networking concepts - Exposure to **O-RAN architectures**, non-RT RIC, rApps, or xApps - Understanding of **autonomy levels** (L1–L4/L5) and operational governance ### Benefits - **Competitive salary, health insurance and Flexible Compensation Plan** as an enterprise benefit - **Annual training budget** to help you stay technologically up to date and grow profesionally - **Time flexibility:** our life is not just a working day; we give you flexibility both in entry and exit. In addition, we wnjoy a reduced working day on Fridays and Summer (July and August) - Our projects are **cutting-edge** in technology and are in both national and international environments, making your growth global - We provide a **flexible working mode**l, adapted to the needs of each role and team, with optio…