Overview
Skills
Job Details
The ideal Developers will be experienced in building and deploying intelligent agents using Google Vertex AI, particularly with Gemini and OpenAI models. The client is large enterprise company in the insurance sector and these roles will join their first dedicated AI/ML team charged with designing and laying a proper AI/ML foundation for the future. Candidates must have experience advising on best practices for AI/ML as well as designing/developing models, agents, frameworks, etc. within a greenfield. As a result, this position requires deep knowledge of large language models (LLMs) and hands-on experience in evaluating model performance using structured testing methodologies.
Key Responsibilities
- Design, develop, and deploy intelligent agents and LLM-driven applications using Google Vertex AI, Gemini, and/or OpenAI models
- Implement structured testing and evaluation frameworks for LLM performance and reliability
- Apply best practices in prompt engineering, context filtering, and security-aware prompting
- Collaborate with AI architects and data engineers to integrate intelligent agents with enterprise systems and data pipelines
- Utilize modern agent frameworks and observability tools for monitoring and improving AI model behavior
- Leverage Google Agent Development Kit, LangChain, LangGraph, LangSmith, and LangFuse to support scalable and maintainable agent design
- Document architectural patterns, testing protocols, and AI lifecycle management practices
- Support continuous improvement initiatives and model optimization across business use cases
Required Skills & Experience
- Bachelor's or Master's degree in Computer Science, Data Science, or a related field
- 7+ years of experience in Python development with a strong focus on AI/ML applications
- Prior experience with Google Cloud Platform (Google Cloud Platform) environments
- Background in machine learning operations (MLOps) and AI system scalability
- Proven hands-on experience with Google Vertex AI, Gemini, and OpenAI model integrations
- Deep understanding of LLM-based architectures, prompt engineering, and AI agent development
- Strong experience using LangChain, LangGraph, LangSmith, and LangFuse frameworks
- Familiarity with observability, logging, and security practices for AI applications
- Excellent communication and collaboration skills to work effectively with cross-functional technical teams
Preferred Experience
- Exposure to vector databases, retrieval-augmented generation (RAG), or semantic search