We are looking for a hands-on AI / LLM Engineer to help design and build practical AI-driven solutions within an existing GCP environment. This role will focus on developing real-world use cases using LLMs, RAG architectures, and agentic workflows to enhance internal tools, automation, and data-driven applications.
Must Haves:
- Experience with AI/ML and LLMs (OpenAI, Vertex AI, or similar)
- Hands-on experience with RAG (Retrieval-Augmented Generation)
- Strong experience with Google Cloud Platform (BigQuery, Dataflow, Vertex AI preferred)
- Experience with AI orchestration tools (LangChain, LlamaIndex, or similar)
- Proficiency in Python (preferred) or backend development
- Experience with APIs and integrating AI into applications
Nice to Have:
- Experience building agent-based or multi-step AI workflows
- Familiarity with vector databases (Pinecone, Weaviate, Vertex AI Vector Search)
- Background in backend development (Java/Spring Boot)
- Experience working in data engineering environments
Key Responsibilities:
- Design and build AI/LLM-based solutions, including RAG pipelines
- Develop and prototype agentic AI workflows for automation and decisioning
- Integrate LLM solutions with existing GCP data platforms (BigQuery, Dataflow)
- Work with structured and unstructured data to enable intelligent retrieval and insights
- Create, test, and optimize prompt engineering strategies
- Collaborate with backend and data engineering teams to embed AI capabilities into applications