Python developer with Gen AI/Agent (Python/GCP)

We are seeking a Python Developer with experience in building AI systems, requiring deep expertise in Python, exposure to leading agent orchestration frameworks (ADK, LangChain, LangGraph), and extensive experience leveraging Google Cloud Platform’s Vertex AI suite.

• Exceptional expertise in Python for ML development, API integration, and leveraging SDKs (Vertex AI SDK, OpenAI SDK).
• Experience in building and orchestrating complex AI workflows using LangChain, LangGraph, and ADK.
• Practical experience developing solutions for core Generative AI tasks including function calling, code generation, classification, summarization, and prompt engineering.
• Knowledge of grounding models using techniques like RAG (Retrieval Augmented Generation).
• Strong working knowledge of GCP GenAI and MLOps tools including Vertex AI Agent Builder, A2A, Managed Compute Platform, Vertex AI Workbench/Notebooks, Vertex AI Pipelines, and Vertex AI Training.

Nice to have:

• Experience with graph databases (e.g., Neo4j) and their integration into LangGraph or RAG systems.
• Experience optimizing GenAI applications for low-latency, high-throughput environments.
• Familiarity with data security principles related to PII/PHI handling within GenAI pipelines and implementing filtering mechanisms.
• Deep experience with running production workloads on GKE or advanced Cloud Run features for model serving.

• Design, develop, and deploy complex, multi-step AI agents using LangChain, LangGraph, and ADK, ensuring efficient state management and execution paths.
• Implement robust mechanisms for agents to utilize external APIs, custom Python functions, and specialized tools to achieve complex goals and interact with enterprise systems.
• Leverage the full suite of Vertex AI services (Agent Builder, Pipelines, Workbench) to manage the entire agent lifecycle, from testing to scalable production deployment.
• Integrate and manage various foundational models (GCP, open source) and utilize Vertex AI Training for model customization.
• Utilize general GCP infrastructure knowledge, including Compute (Agent Engine, GKE, Cloud Run) for deployment, and adhere to networking standards (VPC, Load Balancing, Cloud DNS).
• Implement rigorous testing and logging to monitor agent behavior, optimize token usage, ensure reasoning accuracy, and minimize potential hallucinations.
• Document agent architectures, development processes, and promote reusable design patterns across the engineering team.