Haystack
← Back to Jobs
Technology

Need 14+ Years of AI Engineer (Generative AI & Google Ecosystem) at San Francisco, CA for Long Term Contract

SnapCode IncSan Francisco, CA🇺🇸United StatesPosted 23 Jul 2026

Quick Overview

Work Type
Hybrid
Level
Mid Senior

Job Description

Hi,

Hope you are doing well,
Job Title: AI Engineer (Generative AI & Google Ecosystem)
Location: SFO, CA (2-3days Hybrid)
Duration: 6months
About the Role
We are seeking an innovative and product-driven AI Engineer to join our team and build the next generation of intelligent applications. In this role, you will leverage the power of Google s Gemini models and the broader Google Cloud ecosystem to solve complex problems and create user-centric AI features. You will also heavily utilize open-source frameworks, specifically LangChain and LangGraph, to design, orchestrate, and deploy robust, agentic AI workflows.
If you are passionate about Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and building scalable AI architectures, we want you on our team.
Key Responsibilities
  • Application Development: Design, build, and deploy generative AI applications powered by Google Gemini (Pro, Flash, and Ultra) and Vertex AI.
  • Orchestration & Workflow Design: Utilize LangChain to build complex prompt pipelines and RAG systems. Design and implement stateful, multi-agent workflows and cyclical AI processes using LangGraph.
  • Google Cloud Integration: Architect solutions utilizing the Google Cloud Platform (Google Cloud Platform) ecosystem, including Vertex AI Search and Conversation, BigQuery, Cloud Run, and Google Cloud Storage.
  • Data Pipeline & RAG Engineering: Ingest, process, and chunk diverse data formats. Implement robust vector search architectures using Google Vertex AI Vector Search or open-source vector databases (e.g., Chroma, Milvus).
  • Model Optimization: Employ advanced prompt engineering techniques, few-shot learning, and parameter-efficient fine-tuning (PEFT) to optimize Gemini's performance for specific industry use cases.
  • Evaluation & MLOps: Establish rigorous evaluation metrics for LLM outputs (accuracy, latency, hallucination rates). Deploy models using modern LLMOps practices to ensure observability, scalability, and security.
  • Collaboration: Work closely with product managers, data engineers, and front-end developers to seamlessly integrate AI features into our core products.
Required Qualifications
  • Education: Bachelor s or Master s degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field (or equivalent practical experience).
  • Programming: High proficiency in Python, with a strong grasp of software engineering principles, API development (FastAPI/Flask), and asynchronous programming.
  • AI/LLM Experience: Hands-on experience working directly with LLM APIs (Google Gemini preferred, OpenAI/Anthropic acceptable).
  • Frameworks: Deep understanding of and practical experience with LangChain and LangGraph for building complex LLM applications and autonomous agents.
  • Cloud Infrastructure: Proven experience with Google Cloud Platform (Google Cloud Platform), particularly Vertex AI, IAM, and serverless compute functions.
  • Data & Databases: Experience working with Vector Databases (e.g., Pinecone, Weaviate, Qdrant) and foundational SQL/NoSQL databases.
  • Problem Solving: Strong analytical skills and the ability to debug complex, non-deterministic AI pipelines.
Nice to Have
  • Google Cloud Professional Machine Learning Engineer or Professional Cloud Architect certification.
  • Familiarity with other open-source AI frameworks like LlamaIndex or Hugging Face.
  • Experience with front-end technologies (React, TypeScript) to rapidly prototype AI-driven user interfaces.
  • Experience building and deploying multimodal AI applications (handling text, image, and audio inputs).

Skills

FastAPI
Flask
SQL
MLOps
Machine Learning
BigQuery
Data Pipeline
Generative AI
Google Cloud
Hugging Face
LLM
Python
React
TypeScript

Similar jobs

Apply now