Gen AI Sr. Engineer

Responsibilities

• AI Agent Development (40%): Design, develop, and maintain AI agents and AI-powered applications using Python and ADK. Develop reusable agent frameworks, orchestration workflows, and integrations. Build intelligent workflows leveraging LLMs, RAG, tool calling, and multi-agent systems. Ensure reliability, scalability, observability, and performance of AI agents.
• Cloud Deployment & Operations (25%): Deploy, monitor, and optimize AI applications and agents on Google Cloud Platform. Manage cloud-native services, APIs, compute resources, and AI infrastructure. Implement monitoring, logging, security, and operational best practices. Optimize infrastructure and application performance for cost and efficiency.
• Collaboration & Integration (15%): Partner with data scientists, analysts, architects, and business stakeholders. Translate business requirements into AI-enabled technical solutions. Integrate AI agents into existing enterprise applications and workflows. Participate in solution design, architecture reviews, and stakeholder discussions.
• Infrastructure Automation (10%): Develop Infrastructure as Code (IaC) solutions using Terraform. Automate environment provisioning, deployments, and cloud configurations. Implement CI/CD pipelines supporting AI application lifecycles.
• Quality Engineering & Continuous Improvement (5%): Perform unit testing, integration testing, and troubleshooting. Improve agent evaluation, observability, and operational excellence. Resolve production issues and optimize solution performance.
• Other Duties (5%): Support innovation initiatives and continuous learning. Contribute to AI best practices, standards, and reusable frameworks.

Qualifications

• Educational Qualifications: Engineering Degree BE/ME/BTech/MTech/BSc/MSc. Technical certification in multiple technologies is desirable.

Skills

• Mandatory Skills: Programming & Development Python (Expert level), Object-Oriented Programming (OOP), REST API Development, Microservices Architecture, Git / GitHub, Agentic AI & Generative AI Agent Development Kit (ADK), Agentic AI solutions, Multi-Agent Systems, Prompt Engineering, LLM Integration (Gemini, OpenAI, Claude, etc.), Tool Calling and Function Calling, AI Agent Orchestration Frameworks, Google Cloud Platform (GCP), Vertex AI, Cloud Run, Cloud Functions, Cloud Storage, Pub/Sub, BigQuery, IAM, Monitoring & Logging, Cloud Build, Infrastructure & DevOps, Terraform, CI/CD Pipelines, Docker, Kubernetes (GKE), Infrastructure as Code (IaC), Testing & Operations, Unit Testing, Integration Testing, Debugging & Troubleshooting, Performance Optimization, Monitoring & Observability, L4 L7 (Tech Lead Architect Principal), Proven experience architecting and delivering systems using agentic IDEs, Ability to: Define architectural intent that agents can follow, Break features into agent executable tasks, Govern AI autonomy (guardrails, permissions, reviews), Integrate agentic workflows into CI/CD pipelines, Experience supervising AI agents across: Multi service systems, Legacy modernization, Large codebases / monorepos, Strong understanding of: Security implications of autonomous code execution, Compliance, auditability, and traceability, AI assisted SDLC operating models

Core Responsibility

Guide effective use of agentic IDEs for complex, multi-module or cross-service changes. Establish review practices and quality checks for AI-generated code. Mentor team members on balancing autonomy, correctness, and maintainability in AI-assisted development. Design system architectures that support AI-augmented and agentic development workflows. Define guardrails, standards, and governance for the use of autonomous coding agents. Evaluate impact of agentic IDEs on SDLC, CI/CD pipelines, security posture, and technical debt.