Description

You will design and implement large-scale Generative AI and LLM solutions.

Responsibilities

• Design and build Agentic Workflows using LangChain, LangGraph, or AutoGen.
• Architect Retrieval-Augmented Generation (RAG) systems, selecting vector databases and defining hybrid search strategies.
• Implement Function Calling/Tool Use within LLMs to interface with external REST/gRPC APIs.
• Deploy and manage ML models on Google Cloud Platform (GCP), utilizing Vertex AI and Model Garden on GPUs.
• Apply NLP techniques for intent detection, slot filling, and semantic routing within production systems.

Required Skills

• 8-10 years of professional experience in AI/ML architecture.
• Proven expertise in productionizing Generative AI and Large Language Models (LLMs).
• Deep proficiency in Python and deep learning frameworks (PyTorch or TensorFlow).
• Experience with GCP, specifically Vertex AI and Model Garden.
• Strong background designing RAG architectures and vector database selection (e.g., Milvus, Pinecone).
• Familiarity with NLP techniques for intent detection and semantic routing.
• Experience connecting LLMs to external APIs using Function Calling/Tool Use.

Key Skills

Education

Graduation