About the client
- Azerbaijani telecommunications company and the largest mobile network operator in Azerbaijan.
- Main products include: Fixed telephony, Mobile telephony, Internet services, Wireless broadband, and Value-added services.
About the Role
- The primary goal is to accelerate the client’s Data & AI initiatives via a secure, hybrid cloud foundation on AWS while systematically modernizing the IT estate as part of the AWS MAP 2.0 program.
- Key Project Objectives include:
- Cloud Foundation & Landing Zone: Deploy target hybrid network architectures, establishing a secure AWS Landing Zone Accelerator (LZA) and hybrid Data/AI platforms on AWS.
- Security, Compliance & Sovereignty: Operationalize on-premises data de-identification and Format Preserving Encryption (FPE) tokenization (achieving zero raw PII in the cloud), fully adhering to Azerbaijani Personal Data Law No. 998-IIIQ and Critical Information Infrastructure Rules (Resolution No. 229).
- AI Chatbot & Real-Time Voicebot Implementation: Develop and operationalize a flagship Customer Care Voicebot (STT → LLM → TTS pipeline) and Agentic Chatbot targeting < 2.0s conversational voice latency and ~200 rps throughput as the first hybrid-setup consumer.
What You'll Be Doing
- Lead end-to-end conversational UX and dialogue design for the client’s flagship Customer Care Voicebot and Agentic Chatbot across speech (Avaya) and digital channels (Genesys, Mobile App).
- Define, document, and refine conversational voice personas, turn-taking behavior, barge-in rules, fallback strategies, and human-agent escalation logic across all customer care journeys.
- Craft, test, and optimize prompt engineering strategies for conversational LLMs/SLMs (Amazon Bedrock, SageMaker) specifically tuned for spoken interactions and multi-turn dialogue in Azerbaijani.
- Map multi-agent supervisor/specialist hand-off workflows, intent routing logic, tool invocation contracts (MCP gateways / APIs), and RAG knowledge base retrieval paths in close collaboration with AI Engineers and Architects.
- Partner with Business Analysts, Contact Center SMEs, and CVM teams to integrate offer decisioning contracts, CVM uplift model scores, and Next-Best-Offer (NBO) campaign outputs directly into bot dialogue decision layers.
- Establish dialogue NFR baselines, user experience acceptance criteria, and quality metrics to help guarantee round-trip conversational voice latency < 2.0 seconds.
- Perform prompt engineering, regression testing, and evaluation harness benchmarking for prompt/agent version updates using Amazon Bedrock AgentCore and prompt management tools.
- Collaborate with data labeling and customer care teams to review call/chat transcriptions, analyze intent drop-offs, dialect edge cases, and dissatisfaction signals to continuously iterate dialogue flows.
- Design guardrails, content safety mechanisms, and privacy-compliant interaction flows (ensuring zero raw PII exposure and full adherence to Azerbaijani Personal Data laws).
- Support User Acceptance Testing (UAT), regression testing, and production hypercare for customer care conversational AI flows