Senior Application Support Engineer – AI Products & Agents

Overview

Senior Application Support Engineer – Operations, Reliability & AI Platforms at Eli Lilly and Company, Software Product Engineering team, job level R2. Provides advanced L2 support and escalation for a suite of products, including AI-powered applications and agent-based systems in production.

What you'll do

• Provide advanced technical support for a suite of products, acting as the escalation point for L2 support and customer queries.
• Troubleshoot, diagnose, and resolve incidents related to application functionality, integrations, performance, and security.
• Collaborate with development teams (frontend, backend, full stack) to analyse root causes, reproduce issues, and deliver timely fixes or workarounds.
• Monitor application health, logs, and alerts using tools such as AWS CloudWatch, Winston, or similar.
• Maintain and update knowledge base articles, FAQs, and runbooks for recurring issues and resolutions.
• Support deployment activities, including post-release validation and rollback procedures.
• Participate in incident management, including RCA (Root Cause Analysis), documentation, and communication with stakeholders.
• Ensure compliance with internal standards and external regulations (e.g., GDPR, HIPAA, as relevant).
• Contribute to continuous improvement of support processes.
• Collaborate cross-functionally with Product, QA, Engineering, Platform, and Operations teams to drive product quality and customer satisfaction.
• Support cloud-native and distributed application environments across AWS, Azure, and GCP platforms.
• Drive operational excellence through automation, monitoring, observability, and reliability engineering practices.
• Support AI-powered applications, Generative AI solutions, chatbots, copilots, and agent-based systems running in production environments.
• Troubleshoot and resolve incidents related to AI platforms, LLM integrations, MCP servers, vector databases, retrieval services, and AI orchestration workflows.
• Support deployment, monitoring, performance tuning, and operational stability of AI-enabled applications and services.
• Participate in operational readiness reviews, disaster recovery planning, capacity management, and production support activities for AI workloads.

What you'll need

• 4-6 years of experience in application support, technical troubleshooting, DevOps, Site Reliability Engineering (SRE), or software engineering.
• Demonstrate strong analytical and problem-solving skills, with hands-on experience in debugging web applications (frontend and backend).
• Utilise monitoring, logging, and alerting tools (e.g., AWS CloudWatch, Winston, Datadog, ELK, Splunk, Grafana, Prometheus).
• Work effectively with ticketing systems (e.g., Jira, ServiceNow) and incident management workflows.
• Apply good understanding of RESTful APIs, databases (PostgreSQL, Redis), and cloud platforms (AWS, Azure, GCP).
• Support CI/CD pipelines and deployment processes.
• Use scripting skills (e.g., Bash, Python, JavaScript, PowerShell) for automation and troubleshooting.
• Communicate and collaborate effectively across teams.
• Apply DevOps and Site Reliability Engineering (SRE) practices to improve application reliability, scalability, and operational efficiency.
• Demonstrate understanding of AI application operational support, including monitoring, troubleshooting, observability, and incident management.
• Troubleshoot issues involving Large Language Models (LLMs), AI agents, MCP integrations, AI APIs, prompt orchestration, and retrieval pipelines.
• Support AI application deployments through CI/CD pipelines and automation frameworks.
• Monitor AI service reliability, latency, throughput, failure rates, token consumption, and operational health metrics.
• Implement automation to improve incident response, operational efficiency, and platform reliability.
• Experience supporting products in regulated industries (Life Sciences, Healthcare, Financial Services, etc.).
• Familiarity with frontend frameworks (React, Material-UI) and backend technologies (Node.js, Express.js).
• Knowledge of security best practices and compliance requirements.
• Exposure to Agile methodologies and SDLC.
• Experience with knowledge base management and documentation.
• Interest in continuous learning and process improvement.
• Bachelor's degree in Computer Science, Engineering, or related field (or equivalent practical experience).
• Strong understanding of CI/CD pipelines and deployment automation tools such as GitHub Actions, Azure DevOps, Jenkins, GitLab CI/CD, or similar.
• Experience with Infrastructure as Code (IaC) tools such as Terraform, CloudFormation, or Bicep.
• Understanding of containerization and orchestration technologies such as Docker and Kubernetes.
• Knowledge of application monitoring, observability, alerting, logging, and troubleshooting methodologies.
• Experience supporting production systems in cloud environments.
• Familiarity with release management, change management, incident management, and problem management processes.
• Knowledge of high availability, disaster recovery, backup, failover, and resilience engineering concepts.
• Working knowledge of Generative AI and Large Language Model (LLM) ecosystems.
• Understanding of AI architecture patterns, including LLM-based Applications, Retrieval-Augmented Generation (RAG), AI Agents and Multi-Agent Systems, Prompt Engineering, Vector Databases and Semantic Search, AI Service Integration Patterns, and Agentic Workflows and Orchestration Frameworks.
• Familiarity with Model Context Protocol (MCP), MCP Server architecture, MCP Clients, Tool Calling, and Enterprise AI integrations.
• Understanding of AI observability, monitoring, tracing, evaluation, and operational support practices.
• Exposure to Azure OpenAI, AWS Bedrock, Google Vertex AI, Azure AI Services, OpenAI APIs, Anthropic Claude, or similar AI platforms.
• Knowledge of AI governance, responsible AI practices, security, compliance, and operational risk management.

Nice to have

• Experience supporting AI-enabled enterprise applications, copilots, virtual assistants, chatbots, or agentic systems is highly desirable.
• Experience with SRE principles and operational excellence frameworks.
• Experience implementing self-healing and automated remediation workflows.
• Experience supporting Kubernetes-based applications and cloud-native architectures.
• Familiarity with LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, or similar AI orchestration frameworks.
• Experience supporting MCP-based enterprise integrations and AI tool ecosystems.
• Understanding of AI platform operations, AI FinOps, token management, model monitoring, and cost optimization.
• Experience supporting enterprise-scale observability platforms and AIOps solutions.
• Cloud certifications (AWS, Azure, GCP), DevOps certifications, or AI/Generative AI certifications.
• Experience working in 24x7 support, on-call, or mission-critical production environments.

Details

• Location: Hyderabad, India.
• Non-standard work hours, with some work on weekends and holidays; candidate should be open to working different shifts, 6AM to 2PM and 2PM to 11PM, when required.
• Availability for flexible work hours is/may be required to support continuous operations across two shifts.