Principal Application Support Engineering – AI Products & Agents
Eli Lilly and Company1 day ago
Hyderābād, IndiaStaff+
Responsibilities
- Define operational engineering strategy and reliability standards for enterprise applications, cloud platforms, and AI-enabled systems.
- Lead architecture reviews focused on supportability, observability, resiliency, disaster recovery, and sustainability.
- Own reliability outcomes through SLOs, SLIs, error budgets, operational metrics, and incident trend analysis.
- Lead major incident response, complex troubleshooting, root-cause investigations, post-incident reviews, and corrective actions.
- Establish production readiness reviews, release governance, supportability standards, capacity planning, failover validation, and business continuity practices.
- Provide technical leadership for production AI applications, copilots, virtual assistants, chatbots, AI agents, RAG systems, vector databases, MCP ecosystems, and orchestration platforms.
- Define monitoring for AI quality, token consumption, latency, throughput, reliability, and operational health.
- Drive automation, self-healing capabilities, autonomous remediation, Infrastructure as Code, CI/CD, observability, and AIOps initiatives.
- Establish enterprise runbooks, playbooks, operational standards, and knowledge-management frameworks.
- Mentor engineers and technical leaders and communicate operational risks, health, and strategic recommendations to technical and executive stakeholders.
Requirements
- 10+ years of experience in software engineering, Site Reliability Engineering, DevOps, platform engineering, cloud engineering, production operations, or related disciplines.
- Proven experience operating and supporting large-scale enterprise production environments and leading reliability or operational transformation initiatives.
- Experience in regulated industries such as life sciences, healthcare, financial services, or similar environments.
- Deep knowledge of distributed systems, microservices, APIs, event-driven architectures, cloud-native platforms, software architecture, performance engineering, resiliency, security, and operational excellence.
- Expertise with AWS, Azure, and/or GCP; Kubernetes and Docker; Infrastructure as Code; networking; identity management; cloud governance; high availability; failover; backup; and disaster recovery.
- Experience with GitHub Actions, Azure DevOps, Jenkins, GitLab CI/CD, deployment automation, self-healing systems, and automated remediation.
- Expertise with observability platforms such as OpenTelemetry, Grafana, Datadog, Splunk, ELK, Prometheus, and Dynatrace.
- Strong automation and scripting skills using Python, PowerShell, Bash, JavaScript, or similar technologies.
- Experience supporting LLM applications, RAG, AI agents, multi-agent systems, agentic workflows, semantic search, vector databases, AI orchestration frameworks, and MCP integrations.
- Familiarity with Azure OpenAI, AWS Bedrock, Google Vertex AI, OpenAI APIs, Anthropic Claude, Azure AI Services, LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, or OpenAI Agents SDK is preferred.
- Knowledge of responsible AI, AI governance, security, compliance, model evaluation, operational risk, AIOps, intelligent alerting, event correlation, and operational analytics is preferred.
- Cloud, Kubernetes, DevOps, SRE, or AI/Generative AI certifications and experience with mission-critical global 24x7 environments are preferred.
Benefits
- Flexible work hours and shift-based support for continuous operations, including possible 6AM–2PM and 2PM–11PM shifts.
- Some weekend and holiday work may be required, with appropriate benefits adjustments where applicable.
- Workplace accommodation support is available for applicants with disabilities.
Tech Stack
AWSAzureBashDatadogDockerGitHub ActionsGitLab CI/CDGoogle Cloud PlatformGrafanaJavaScriptJenkinsKubernetesPowerShellPrometheusPythonSplunkTerraform
Categories
DevOpsSite Reliability
About Eli Lilly and Company
Eli Lilly and Company researches, develops, manufactures, and markets prescription medicines and biologics for patients, sold through healthcare providers, pharmacies, and payers. Core therapeutic areas include diabetes, oncology, immunology, neuroscience, and obesity. Founded in 1876 and headquartered in Indianapolis, it is a public company (NYSE: LLY) with global operations and is building a new advanced manufacturing site for gene therapy and other modalities in Lebanon, Indiana.