About the Role :
We are looking for an experienced Python GCP AI Engineer with expertise in Google Cloud Platform (GCP), Vertex AI, and Agentic AI development. The ideal candidate should have strong experience in designing, developing, and deploying AI-powered applications using Large Language Models (LLMs), multi-agent systems, and cloud-native AI services.
Key Responsibilities :
- Design, develop, and deploy AI-powered applications using Python, GCP, and Vertex AI.
- Build and implement Agentic AI solutions using Google Agent Development Kit (ADK) or similar agent frameworks.
- Design, develop, and optimize Multi-Agent Systems (MAS) for complex business workflows.
- Develop AI workflows involving LLM orchestration, prompt engineering, retrieval, and agent collaboration.
- Evaluate, benchmark, and improve AI models using established evaluation frameworks and performance metrics.
- Fine-tune LLMs and optimize inference performance for production environments.
- Deploy, monitor, and maintain AI applications on Google Cloud Platform.
- Implement Human-in-the-Loop (HITL) workflows to improve model accuracy and user experience.
- Perform root cause analysis, debugging, and performance optimization for AI applications.
- Work with long-context LLMs and optimize memory, context management, and response quality.
- Collaborate with business stakeholders and customers to understand requirements and translate them into scalable AI solutions.
- Maintain technical documentation and follow software engineering best practices throughout the development lifecycle.
Required Skills :
- 8 - 10 years of software development experience with strong expertise in Python.
- Hands-on experience with Google Cloud Platform (GCP) and Vertex AI.
- Experience developing Agentic AI applications using Google ADK or similar frameworks.
- Strong understanding of Multi-Agent Systems (MAS) and AI workflow orchestration.
- Experience with LLMs, prompt engineering, model evaluation, and fine-tuning techniques.
- Knowledge of AI evaluation frameworks, benchmarking, and performance metrics.
- Experience deploying AI applications in cloud environments.
- Strong debugging, troubleshooting, and root cause analysis skills.
- Excellent communication and stakeholder management skills.
Preferred Skills :
- Experience with LangChain, LangGraph, CrewAI, AutoGen, Google ADK, or similar agent frameworks.
- Knowledge of RAG (Retrieval-Augmented Generation) architectures and vector databases.
- Experience with Docker, Kubernetes, and CI/CD pipelines.
- Familiarity with BigQuery, Cloud Run, Cloud Functions, and other GCP services.
- Exposure to MLOps, model monitoring, and AI governance practices.