AI Engineer Development / 5-10 years

Miracle Software Systems, Inc.; Mountain View (CA); Hybrid; USD 100,000 - 150,000; Full time

Job summary

A software solutions company is seeking a skilled professional to design stateful workflows, develop generative AI applications, and architect AI services on Google Cloud Platform. Key responsibilities include building REST APIs in Python, developing data pipelines, and optimizing system performance. Candidates should possess strong skills in AI technologies and software development, along with a collaborative approach to work. This role offers opportunities to engage with innovative projects in the AI domain.

Responsibilities

• Design and implement stateful, multi-agent workflows using LangGraph.
• Develop generative AI applications integrating enterprise data sources.
• Architect and deploy AI services on Google Cloud Platform.
• Build and maintain REST APIs in Python frameworks.
• Develop data pipelines, embeddings, and retrieval layers.
• Implement Retrieval-Augmented Generation architectures.
• Optimize prompts and manage production workloads.

Skills

Design and implement workflows

Develop generative AI applications

Architect and deploy AI services

Build REST APIs in Python

Develop data pipelines

Optimize prompts and manage workloads

Collaborate with product owners

Tools

Google Cloud Platform

Vertex AI

Python

FastAPI

Flask

Git

BigQuery

Job description

Thanks for contacting us, we will get back to you soon

Upload Resume * Upload PDF/DOC only. Max 2MB

Work Authorization

Do you want to subscribe our newsletter?

We are an Equal Opportunity Employer

Applicants are considered for employment without attention to or discrimination against race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status. All employment is decided on the basis of qualifications, merit and business need.

• Design and implement stateful, multi-agent workflows using LangGraph and the Google Agent Development Kit.
• Develop generative AI applications that integrate enterprise data sources using Model Context Protocol (MCP) for secure LLM interaction.
• Architect and deploy AI services on Google Cloud Platform using Vertex AI, Cloud Run, and Cloud Functions.
• Build and maintain REST APIs in Python using frameworks such as FastAPI or Flask to expose AI capabilities.
• Develop data pipelines, embeddings, and retrieval layers using BigQuery and vector databases.
• Implement Retrieval-Augmented Generation architectures and establish evaluation mechanisms to monitor response quality, accuracy, and performance.
• Optimize prompts, monitor model latency, and manage production workloads for reliability and cost control.
• Maintain version control using Git and contribute to CI/CD pipelines for automated deployment.
• Collaborate with product owners and platform teams while producing design documentation, runbooks, and production support during rollout.

Applicants are considered for employment without attention to or discrimination against race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status. All employment is decided on the basis of qualifications, merit and business need.

Thanks for submitting your profile, we will update you back with a suitable position