GenAI Engineer

Quick Facts

• Role: GenAI Engineer

• Location: Austin, TX; Houston, TX; San Antonio, TX; Dallas, TX

• Engagement: 12+ months

Description

You will design and build next-generation Generative AI applications on Google Cloud using Google Gemini and Vertex AI. The role focuses on production-grade LLM integrations, RAG, and stateful multi-agent workflows using LangChain and LangGraph, along with scalable cloud-native architectures. You will also implement vector search, data ingestion pipelines, LLM evaluation, and LLMOps practices, and expose AI services via REST APIs.

Responsibilities

• Design, develop, and deploy Generative AI applications using Google Gemini (Pro, Flash, Ultra) and Vertex AI

• Build advanced prompt pipelines, RAG applications, and AI workflows using LangChain

• Design and implement stateful, multi-agent AI systems using LangGraph

• Develop scalable AI solutions using Google Cloud services including Vertex AI Search, BigQuery, Cloud Run, Cloud Storage, and IAM

• Build robust data ingestion pipelines supporting multiple document formats

• Implement vector search architectures using Vertex AI Vector Search or vector databases such as Chroma, Milvus, Pinecone, Weaviate, or Qdrant

• Optimize LLM performance using prompt engineering, few-shot learning, and PEFT techniques

• Establish evaluation metrics for LLM accuracy, latency, hallucination detection, and model performance

• Implement LLMOps best practices including observability, scalability, monitoring, and security

• Develop REST APIs using FastAPI or Flask to expose AI services

• Collaborate with Product Managers, Data Engineers, and Front-End Developers to integrate AI capabilities into enterprise applications

Requirements

• Strong programming experience in Python

• Experience building REST APIs using FastAPI or Flask

• Hands-on experience with Google Gemini APIs, Vertex AI, and other enterprise LLM platforms

• Strong expertise with LangChain and LangGraph

• Experience implementing RAG architecture

• Strong knowledge of Google Cloud Platform

• Experience with Vertex AI, IAM, Cloud Run, BigQuery, and Google Cloud Storage

• Experience working with vector databases including Pinecone, Weaviate, Qdrant, Chroma, or Milvus

• Strong SQL and NoSQL database experience

• Experience debugging complex AI pipelines and distributed applications

• Strong problem-solving and communication skills

Benefits

• 12+ months engagement