Python/GenAI Developer

cai; Pennsylvania; Remote; USD 120,000 - 180,000; Full time

Job summary

CAI is seeking a Python/GenAI Developer to build and support Python-based backend services and AI solutions leveraging LLMs, RAG, FastAPI, and Google Cloud technologies. The role is remote and contract, focusing on secure, scalable AI-enabled applications.

You will collaborate with stakeholders across the SDLC, implement generative AI workflows, and contribute to reliable AI pipelines with strong coding practices and documentation.

Qualifications

• 4-7 years of software development experience with Python backend development
• 1-2 years of practical Generative AI and LLM-based applications including prompt engineering and structured outputs
• 1-2 years of practical RAG solutions including document ingestion and embeddings
• Experience building REST APIs using FastAPI, Flask, or similar frameworks
• Hands-on experience with Google Cloud Platform: Cloud Run, Cloud Storage, Vertex AI, BigQuery, Pub/Sub, IAM, Secret Manager

Responsibilities

• Design, develop, and maintain Python-based backend services and APIs for AI-enabled applications with clean, production-ready code
• Build and integrate Generative AI workflows using LLMs, RAG pipelines, prompts, and structured outputs
• Develop FastAPI-based REST endpoints to support file processing, pipeline execution, and integration with external enterprise apps
• Implement retrieval workflows using GCP services such as Vertex AI, Cloud Storage, BigQuery, Pub/Sub
• Develop data-processing logic for structured and unstructured inputs, including parsing and transformation
• Support testing, deployment, logging, monitoring, and troubleshooting of AI apps across environments
• Collaborate with solution architects and stakeholders to translate requirements into AI features and scalable backend components
• Contribute to prompt engineering, output validation, error handling, and guardrails for reliability
• Maintain API contracts, configuration files, and deployment artifacts

Skills

Python backend

Generative AI

LLM

REST APIs

FastAPI

GCP

Docker

Git

CI/CD

Agile

Tools

FastAPI

Flask

Google Cloud Platform

Vertex AI

BigQuery

Pub/Sub

Cloud Run

Docker

GitHub/GitLab

Job description

Python/GenAI Developer

Req number: R8777

Employment type: Full time

Worksite flexibility: Remote

Who we are

CAI is a global services firm with over 9,000 associates worldwide and a yearly revenue of $1.3 billion+. We have over 40 years of excellence in uniting talent and technology to power the possible for our clients, colleagues, and communities. As a privately held company, we have the freedom and focus to do what is right-whatever it takes. Our tailor-made solutions create lasting results across the public and commercial sectors, and we are trailblazers in bringing neurodiversity to the enterprise.

Job Summary

As a Python/GenAI Developer, you will Build and enhance enterprise AI applications through Python development, Generative AI integration, API design, data processing, and cloud-based deployment.

Job Description

CAI is seeking a Python/GenAI Developer to build and support Python-based backend services and AI solutions leveraging LLMs, RAG, FastAPI, and Google Cloud technologies. The role focuses on delivering secure, scalable, and reliable AI-enabled applications while collaborating with business and technical stakeholders throughout the software development lifecycle. This position is contract and remote.

What You'll Do

• Design, develop, and maintain Python-based backend services and APIs for AI-enabled applications, with strong emphasis on clean, modular, production-ready code
• Build and integrate Generative AI workflows using LLMs, RAG pipelines, prompt orchestration, and structured-output processing
• Develop FastAPI-based REST endpoints to support file processing, pipeline execution, asynchronous workflows, and integration with external enterprise applications
• Implement retrieval workflows using GCP services such as Vertex AI, Vertex AI Search, Cloud Storage, BigQuery, Pub/Sub, Secret Manager, and Cloud Run
• Develop data-processing logic for structured and unstructured inputs, including document parsing, metadata generation, validation, transformation, and downstream persistence
• Support integration testing, debugging, deployment, logging, monitoring, and troubleshooting of AI applications across development and QA environments
• Collaborate with solution architects, cloud infrastructure teams, product owners, and business stakeholders to translate requirements into working AI features and scalable backend components
• Contribute to prompt engineering, output validation, error handling, retry logic, and guardrails to improve reliability of AI pipeline responses
• Maintain technical documentation, API contracts, configuration files, deployment artifacts, and reusable engineering components

What You'll Need

Required:

• Minimum 4-7 years of software development experience, with strong hands-on experience in Python backend development; programming fundamentals, object-oriented design, modular coding, exception handling, testing, and package management
• Minimum 1-2 years of practical experience with Generative AI and LLM-based applications including prompt engineering, structured outputs, model invocation, response validation, token usage, and basic evaluation concepts
• Minimum 1-2 years of practical experience RAG solutions including document ingestion, chunking, embeddings, vector retrieval, metadata filtering, reranking, and grounding
• Experience building REST APIs using FastAPI, Flask, or similar Python frameworks; endpoint development, request/response models, authentication, async processing, status handling, and API integration
• Hands-on experience working with Google Cloud Platform, especially 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 cloud-native development including Docker, service accounts, environment variables, secrets, CI/CD, deployment, and runtime troubleshooting
• Experience processing structured and unstructured data formats such as JSON, JSONL, Excel, CSV, PDF, Word documents, and text
• Experience with source control, CI/CD, containerization, and deployment workflows using Git, Docker, GitLab/GitHub, and cloud deployment pipelines
• Exposure to debugging distributed or cloud-hosted applications using logs, monitoring, request tracing, and error analysis
• Experience working in Agile delivery teams and collaborating with cross-functional stakeholders

Preferred:

• Experience with Agentic AI frameworks or multi-step AI orchestration
• Familiarity with Vertex AI Vector Search, Graph RAG, or knowledge graph concepts
• Experience with Pub/Sub-based asynchronous processing and event-driven architectures
• Understanding of OAuth, service-to-service authentication, IAM, signed URLs, and secure API integration
• Exposure to React or frontend integration is useful but not mandatory
• Familiarity with AI evaluation metrics such as groundedness, relevance, completeness, coherence, and confidence scoring
• Healthcare-domain exposure