Job Description

Salary: $80,000 - 110,000 per year Requirements:

• 4–7 years of software development experience, including strong hands-on Python backend development.
• 1–2 years of practical experience building Generative AI, LLM-based, or RAG applications.
• Experience developing REST APIs with FastAPI, Flask, or a similar Python framework; FastAPI is preferred.
• Hands-on GCP experience with Cloud Run, Cloud Storage, Vertex AI, BigQuery, Pub/Sub, IAM, and Secret Manager.
• Experience integrating AI/ML services into enterprise applications using APIs, authentication, asynchronous processing, and cloud-native services.
• Experience with structured and unstructured data formats, Git, Docker, CI/CD, cloud deployment, debugging, and Agile collaboration.
• Proficiency in Python fundamentals, including object-oriented and modular coding, exception handling, unit testing, and package management.
• Knowledge of Generative AI concepts, including prompts, model invocation, structured outputs, token usage, response validation, and basic evaluation.
• Knowledge of RAG workflows, including ingestion, chunking, embeddings, vector retrieval, metadata filtering, reranking, and grounding.
• Familiarity with FastAPI/REST endpoint design, request and response models, authentication, asynchronous processing, and integration.
• Experience processing data with tools and formats such as pandas, openpyxl, JSON/JSONL, Excel, CSV, PDF, Word, and text.
• Familiarity with service accounts, secrets, CI/CD, Postman or cURL, logging, and troubleshooting.
• Additional desired experience includes agentic AI frameworks, multi-step orchestration, Vertex AI Vector Search, Graph RAG, knowledge graphs, Pub/Sub event-driven architectures, OAuth, signed URLs, secure service-to-service authentication, React or frontend integration, AI evaluation metrics, and healthcare workflows or document intelligence.
• No specific degree requirement is stated.

• Design, develop, and maintain modular Python backend services and APIs for AI-enabled applications.
• Build LLM and RAG pipelines, including prompt orchestration, structured output processing, validation, and guardrails.
• Develop REST APIs, preferably with FastAPI, for document processing, pipeline execution, asynchronous operations, and enterprise integrations.
• Implement retrieval and processing workflows using Google Cloud services, including Vertex AI, Vertex AI Search, Cloud Storage, BigQuery, Pub/Sub, Secret Manager, and Cloud Run.
• Process structured and unstructured documents through parsing, metadata generation, validation, transformation, and persistence.
• Support integration testing, debugging, deployment, logging, monitoring, and troubleshooting in development and QA environments.
• Collaborate with architects, infrastructure teams, product owners, and stakeholders to deliver scalable AI functionality.
• Maintain API contracts, documentation, configuration, deployment artifacts, and reusable components.

• Agentic AI
• AI
• API
• BigQuery
• Backend
• CI/CD
• Cloud
• Docker
• Excel
• FastAPI
• Flask
• Frontend
• GCP
• Git
• IAM
• Support
• JSON
• LLM
• OAuth
• Postman
• Python
• RAG
• REST
• React
• pandas
• OOP

More:

We are hiring for a three-month contract role developing production-ready Python backend services and APIs for AI-enabled enterprise applications. The work focuses on Generative AI and RAG solutions that integrate with Google Cloud Platform. The role involves cloud-hosted engineering in Agile, cross-functional teams and requires supporting development and QA environments. Location, remote or onsite schedule, and travel expectations are not specified.

last updated 43 week of 2026

Job Tags

Similar Jobs