Cloud AI Engineer (RAG Platform)

As a recruitment company, DCG understands that every business is powered by experienced professionals. Our management style and partnership approach enable us to meet your needs and provide continuous support. Due to our ongoing growth and the large number of recruitment projects we undertake for our partners, we are currently looking for:

Cloud AI Engineer (RAG Platform)

Responsibilities:

• Architect & Develop: Design, develop, test, and deploy a scalable and secure RAG (Retrieval Augmented Generation) service using Python and serverless AWS technologies

• Infrastructure as Code: Define and manage all required AWS infrastructure using the AWS Cloud Development Kit (CDK)

• Data Ingestion & Processing: Implement robust pipelines for processing and embedding unstructured data (e.g., PDF, DOCX, HTML), making it ready for semantic search and retrieval

• API Development: Build and maintain a RESTful API for the service

• CI/CD & Automation: Maintain CI/CD pipelines (GitLab CI)

• Monitoring & Optimization: Implement comprehensive monitoring and logging to track service health, performance, and cost. Proactively identify and resolve bottlenecks or issues

• Collaboration: Work closely with our cloud engineering, data science, and AI Platform teams to ensure seamless integration, operational excellence, and alignment with company-wide standards

• Focus on delivering value to business users

Requirements:

• Experience: 3+ years of professional software engineering experience with a Focus on Python, including designing and building scalable, production-grade applications

• Cloud Expertise: 3+ years of hands-on experience with AWS(AWS Lambda, Step Functions, IAM, VPC, S3, DynamoDB,API Gateway, CloudFormation / CDK)

• API Development: Proven experience building and managing high-volume RESTful APIs, with a strong understanding of best practices for performance and security

• DevOps: Experience with Docker and building CI/CD pipelines (GitLab CI is a plus)

• AI/ML Fundamentals: A strong conceptual and practical understanding of GenAI concepts, particularly embedding models, vector search, and reranking algorithms

• GenAI Frameworks: Hands-on experience with agentic or RAG-specific frameworks like LangChain or LlamaIndex

• Strong sense of ownership and a proactive approach to new tasks or any issues

• Strong verbal and written communication skills in English Preferred Qualifications

• Modern Python: Expertise in modern Python development practices, including type hints, uv package manager, and data validation libraries like Pydantic

• Data Parsing: Specific experience with complex data extraction challenges, such as parsing intricate PDF files or other unstructured document formats

• Observability: Experience with monitoring and observability tools like AWS CloudWatch, Grafana, or similar

• Cross-Cloud Knowledge: Familiarity with comparable services on other clouds,such as Azure AI Search

• Experience working with AI Code Assistants (Copilot, Claude Code)

Nice to have:

• GxP Experience: Previous experience working on projects in a regulated GxP environment

Offer:

• Private medical care

• Co-financing for the sports card

• Training & learning opportunities

• Constant support of dedicated consultant

• Employee referral program