Service Delivery Manager (DFS)

Noida, Uttar Pradesh

Job Summary

Job Description : Agentic AI Developer\\r\\nAI for Data Center & Cloud Services\\r\\nRole: Agentic AI Developer\\r\\nLevel: Mid-level (8-12 years of experience)\\r\\nFunction: AI Engineering / Cloud & Infrastructure Services\\r\\nWork Model: Hybrid\\r\\nReports To: [Hiring Manager / Head of AI Engineering]\\r\\nOpenings: 1\\r\\n\\r\\nAbout the Role\\r\\nWe are hiring an Agentic AI Developer to design, build, and operationalize AI agents and copilots that support our Data Center (DC) and Cloud services teams. In this role, you will partner directly with customer infrastructure teams to identify high-value AI use cases, prototype agentic workflows, and ship production-grade solutions that automate operational tasks, accelerate incident response, and streamline cross-functional processes.\\r\\nThis is a hands-on engineering role with strong customer exposure. You will work across LLM frameworks, orchestration tooling, cloud platforms, and existing infrastructure systems to translate ambiguous infra problems into reliable, measurable AI agents.\\r\\nKey Responsibilities\\r\\nAgent Design & Development\\r\\n• Design, build, and deploy agentic AI solutions (single-agent and multi-agent) for DC and cloud operations use cases.\\r\\n• Implement LLM-powered workflows using modern frameworks (e.g., LangGraph, LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, or equivalent).\\r\\n• Develop robust tool integrations, function calls, and APIs that let agents interact with monitoring, ticketing, CMDB, CI/CD, and cloud control planes.\\r\\n• Implement guardrails, evaluations, and observability for agent behavior, including prompt versioning, tracing, and quality metrics.\\r\\nCustomer & Infra Use Case Delivery\\r\\n• Engage with customer infrastructure teams to discover, qualify, and prioritize AI use cases across compute, storage, network, virtualization, and cloud.\\r\\n• Build AI agents for areas such as: incident triage and remediation, change risk analysis, capacity and cost optimization, log and alert summarization, runbook automation, knowledge retrieval, and policy/compliance checks.\\r\\n• Translate operational SOPs and runbooks into structured, agent-executable workflows.\\r\\n• Run rapid POCs, demos, and pilots; iterate based on customer feedback and operational metrics.\\r\\nProcess Management & Automation\\r\\n• Identify recurring manual processes within service delivery and operations, and automate them using agentic AI combined with existing automation tooling.\\r\\n• Build copilots that assist engineers across ITSM workflows (incident, change, problem, request) and reduce handling time.\\r\\n• Define KPIs (deflection rate, MTTR reduction, automation coverage, accuracy)



and continuously improve agents against them.\\r\\nEngineering Excellence\\r\\n• Write clean, tested, well-documented Python code; follow secure-by-design and privacy-by-design principles.\\r\\n• Containerize and deploy agents on cloud-native platforms; integrate with CI/CD pipelines.\\r\\n• Apply responsible AI practices: data handling, PII redaction, access controls, model evaluation, and hallucination mitigation.\\r\\n• Collaborate with platform, data, security, and infrastructure teams to ensure solutions are scalable, observable, and supportable.\\r\\nRequired Qualifications\\r\\n• Bachelor\\\'s degree in Computer Science, Engineering, or a related field (or equivalent practical experience).\\r\\n• 3 to 5 years of software engineering experience, with at least 1 to 2 years building LLM-based or agentic AI applications.\\r\\n• Strong Python skills and solid fundamentals in data structures, APIs, and asynchronous programming.\\r\\n• Hands-on experience with LLM/agent frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, or similar.\\r\\n• Practical experience with at leas

Key Responsibilities

Agent Design & Development • Design, build, and deploy agentic AI solutions (single-agent and multi-agent) for DC and cloud operations use cases. • Implement LLM-powered workflows using modern frameworks (e.g., LangGraph, LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, or equivalent). • Develop robust tool integrations, function calls, and APIs that let agents interact with monitoring, ticketing, CMDB, CI/CD, and cloud control planes. • Implement guardrails, evaluations, and observability for agent behavior, including prompt versioning, tracing, and quality metrics. Customer & Infra Use Case Delivery • Engage with customer infrastructure teams to discover, qualify, and prioritize AI use cases across compute, storage, network, virtualization, and cloud. • Build AI agents for areas such as: incident triage and remediation, change risk analysis, capacity and cost optimization, log and alert summarization, runbook automation, knowledge retrieval, and policy/compliance checks. • Translate operational SOPs and runbooks into structured, agent-executable workflows. • Run rapid POCs, demos, and pilots; iterate based on customer feedback and operational metrics.



Process Management & Automation • Identify recurring manual processes within service delivery and operations, and automate them using agentic AI combined with existing automation tooling. • Build copilots that assist engineers across ITSM workflows (incident, change, problem, request) and reduce handling time. • Define KPIs (deflection rate, MTTR reduction, automation coverage, accuracy) and continuously improve agents against them. Engineering Excellence • Write clean, tested, well-documented Python code; follow secure-by-design and privacy-by-design principles. • Containerize and deploy agents on cloud-native platforms; integrate with CI/CD pipelines. • Apply responsible AI practices: data handling, PII redaction, access controls, model evaluation, and hallucination mitigation. • Collaborate with platform, data, security, and infrastructure teams to ensure solutions are scalable, observable, and supportable.

Skill Requirements

Bachelor's degree in Computer Science, Engineering, or a related field (or equivalent practical experience). • 3 to 5 years of software engineering experience, with at least 1 to 2 years building LLM-based or agentic AI applications. • Strong Python skills and solid fundamentals in data structures, APIs, and asynchronous programming. • Hands-on experience with LLM/agent frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, or similar. • Practical experience with at least one major cloud provider (AWS, Azure, or GCP), including identity, networking, and core compute/storage services. • Experience integrating LLMs with external tools, APIs, vector stores (e.g., pgvector, Pinecone, Weaviate, FAISS), and enterprise data sources. • Understanding of prompt engineering, RAG patterns, evaluations, and basic MLOps/LLMOps practices. • Familiarity with data center and/or cloud infrastructure concepts: virtualization, storage, networking, monitoring, ITSM, and automation. • Robust communication skills; ability to work directly with customer infra teams and translate technical work into business outcomes.

Other Requirements

Experience building multi-agent systems, planner-executor architectures, or tool-using autonomous agents in production. • Exposure to infrastructure-as-code (Terraform, Ansible) and observability stacks (Prometheus, Grafana, ELK, Datadog, Splunk). • Experience with ITSM platforms (ServiceNow, Jira Service Management) and integrating AI into incident/change workflows. • Experience with container platforms (Docker, Kubernetes) and serverless runtimes. • Knowledge of AI safety, evaluation frameworks (e.g., Ragas, DeepEval, custom evals), and red-teaming techniques. • Prior experience in a managed services, MSP, or hyperscaler environment supporting external customers.

📌 Service Delivery Manager (DFS) (India)
🏢 HCLTech
📍 India