Assistant Manager - Customer Interaction Suite

Tata Communications Redefines Connectivity with Innovation and IntelligenceDriving the next level of intelligence powered by Cloud, Mobility, Internet of Things, Collaboration, Security, Media services and Network services, we at Tata Communications are envisaging a New World of Communications

Job Title: Assistant Manager – CX Technical Support Engineer Job Summary Technical Support Engineer plays a critical role in ensuring the stability, performance, and reliability of AI\-driven platforms and enterprise applications being a part of function AI Operation. This role focuses on incident management, root cause analysis, monitoring, troubleshooting, and operational support for production systems. Technical Support Engineer act as the bridge between L1 support teams and L3 engineering/development teams, ensuring quick resolution of issues and continuous service improvement. Key Responsibilities Operational Support \& Incident Management Provide Level 2 support to Technical Service Desk for AI platforms, applications, and underlying infrastructure. Investigate, diagnose, and resolve production incidents, service disruptions, and performance issues. Perform root cause analysis (RCA) and document incident reports with corrective and preventive actions. Escalate complex issues to SRE teams with detailed analysis and logs. Observability \& Monitoring Management Monitor application health, system performance, resource utilization, alert noise using monitoring tools and dashboards. Identify recurring issues and proactively suggest improvements to enhance system stability. Tune system parameters to improve performance and reliability. AI \& Automation Supervision. Validate AI decisions (false positives / false RCA) Support AI/ML platforms, APIs, databases, and middleware in production. Participate in shift handovers and operational review meetings. Documentation \& Continuous Improvement Maintain runbooks, SOPs, knowledge articles, and operational documentation. Identify automation opportunities to reduce manual effort and improve response times. Contribute to operational excellence initiatives and best practices. Mandatory Skills A hands\-on AI Operations / Support Engineer with experience supporting production AI platforms, applications, and cloud infrastructure in 24×7 environments. Minimum 2 years industry work experience to operate and support AI driven CX services, including LLM based bots, Voice AI, Chat, STT/TTS, NLP, and sentiment analysis. Minimum 2 years Working knowledge of prompt engineering, including writing clear prompts and validating AI responses for accuracy, relevance, and quality. Minimum 2 years, experience supporting production AI workflows and customer facing conversational journeys. Knowledge of Safety/Guardrails: Ragas or DeepEval, policy enforcement. Hands on experience with Linux/Unix systems including shell Scripting. Knowledge of observability and monitoring tools (eg. New Relic, Prometheus, Kube Prometheus Stack, Grafana (including Loki / database backed logs), ELK / OpenSearch, ES Cloud, Slack) Strong development skills of Python with FastAPI, along with hands on experience using Git for version control. Minimum 2 years of hands on development experience with MySQL or PostgreSQL or any other SQL, including schema design, query optimization, indexing, and troubleshooting database related performance issues. Strong troubleshooting skills with a structured, data\-driven approach. Clear verbal and written communication skills for technical and non\-technical audiences. Qualifications Bachelor’s degree in computer science, Computer Science (Date Science), Computer Science (Artificial Intelligence/ Machine Learning), or Software Engineering. 2–5 years of experience in AI based eco systems and prompt engineering Preferred Skills Agent frameworks: LangChain, AutoGen, Semantic Kernel. Certification \- Generative AI with Large Language Models or LLMOps KPIs Ticket response time and resolution time SLA compliance Customer satisfaction score Incident escalation accuracy System uptime monitoring effectiveness