Description

Build, deploy, and operate GenAI-powered tools to accelerate network troubleshooting, including triage assistants, KPI summaries, and anomaly detection with source citations.

This role is on-site.

Responsibilities

• Design and implement RAG pipelines: document preparation (chunking/metadata), embeddings, vector search with re-ranking, grounding, citation strategies, semantic caching, and safety guardrails.
• Ship reliable services by productionizing models and prompts using CI/CD, automated tests, canary/A–B releases, and monitoring with SLOs for accuracy, grounding, latency, and cost.
• Implement evaluation and continuous monitoring: offline/online eval harnesses, golden sets, human-in-the-loop review, prompt/knowledge drift detection, and token/cost budgets.
• Integrate with internal systems (alarms, KPI platforms, ticketing, inventory/topology APIs, runbooks, dashboards) to close the loop from detection to remediation.
• Collaborate with data engineering, platform/security, and RAN SMEs to iterate use cases based on measurable impact like MTTR reduction and accuracy lift.

Required Skills

• 3–5 years of experience in AI/ML engineering, data engineering, or applied data science delivering production-grade solutions.
• Strong Python and SQL skills; mastery working with large-scale telemetry/time-series datasets and building reliable, testable data transformations.
• Hands-on experience with Azure services: Azure Machine Learning, Azure AI Services/Azure OpenAI, Azure AI Search (vector/hybrid search), Azure Data Factory, Azure DevOps, and Kubernetes (AKS).
• Production mindset: robust logging/monitoring, tracing, observability (OpenTelemetry), troubleshooting, and security basics (RBAC, managed identities, Key Vault, data privacy/PII handling).
• GenAI development patterns: RAG (chunking, embeddings, hybrid search, re-ranking, grounding), prompt design (system prompts, few-shot, structured JSON/JSON Schema, function/tool calling).
• Evaluation fundamentals: response quality, grounding, accuracy, latency, cost, and safety metrics.
• LLMOps/MLOps practices: CI/CD for pipelines/services, model/prompt/knowledge versioning, automated evaluations, drift monitoring, and cost/token controls.

Preferred Skills

• Solid understanding of 4G/5G RAN and mobility concepts (handovers, drops, throughput, congestion, interference, PRB utilization, RSRP/RSRQ/SINR) and ability to translate network issues into measurable KPIs.
• Experience with agentic workflows and orchestration (multi-step chains, retries/guardrails) to automate diagnosis and propose actions.
• Familiarity with GenAI frameworks (Semantic Kernel, LangChain/LlamaIndex), MLflow/Model Registry, and vector databases.

Referral Bonus: ₹50,000

Key Skills

Education

Bachelor's degree