Senior AWS AI Engineer
Posted 1ds ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Senior AWS AI Engineer designing production-grade Bedrock and RAG solutions. Helping Keyrus industrialise AI for organisations through cloud engineering and client delivery.
Responsibilities:
- Design and implement serverless and cloud-native architectures on AWS
- Build and deploy Generative AI applications using Amazon Bedrock, foundation models, Knowledge Bases, Agent capabilities, guardrails, and related AWS services
- Develop AI applications and services using Python and Boto3
- Design and implement production-grade Retrieval-Augmented Generation solutions using Amazon OpenSearch, Bedrock Knowledge Bases, vector search technologies, and LLMs
- Design and optimise RAG pipelines, including chunking strategies, retrieval optimisation, metadata filtering, and context management
- Implement semantic search solutions using Amazon OpenSearch
- Design and build agent-based architectures using Bedrock Agents and AgentCore capabilities
- Develop prompt engineering frameworks and reusable prompting strategies
- Implement LLM evaluation methodologies, including LLM-as-a-Judge and automated evaluation frameworks
- Design model routing and inference optimisation strategies
- Apply GenAI observability, monitoring, and operational best practices
- Contribute to AI governance, evaluation, and responsible AI initiatives
- Support the industrialisation of AI solutions into scalable production environments
- Collaborate with Cloud Engineers, Data Engineers, Architects, and client stakeholders
- Contribute to AI engineering best practices, standards, and reusable frameworks
Requirements:
- Relevant academic background in Computer Science, Software Engineering, Information Technology, or equivalent practical experience
- 5+ years of experience in AWS Cloud Engineering, Software Engineering, or Cloud Solution Development
- 2+ years of hands-on experience building and deploying Generative AI and LLM-based applications
- Proven experience designing and implementing cloud-native architectures on AWS
- Demonstrated experience implementing at least one production-grade RAG solution
- Experience working in agile delivery teams and multidisciplinary technical environments
- Professional proficiency in English
- Expertise in Amazon Bedrock, including Foundation Models, Knowledge Bases, Bedrock Agents, and AgentCore capabilities
- Experience designing, implementing, and optimising RAG architectures, retrieval pipelines, and AI-powered applications
- Strong Python and Boto3 development skills
- Experience with semantic search, Amazon OpenSearch, vector-based retrieval, metadata filtering, and search optimisation techniques
- Understanding of agentic architectures, multi-step reasoning workflows, and orchestration patterns for GenAI applications
- Experience with prompt engineering, prompt evaluation, and techniques for improving LLM response quality and reliability
- Knowledge of LLM evaluation frameworks, including LLM-as-a-Judge, observability, monitoring, testing, and responsible AI practices
- Understanding of LLM FinOps, model routing strategies, inference optimisation, and cost-performance trade-offs
- Experience building APIs, integrating enterprise applications, and developing production-grade software solutions using modern engineering practices
- French proficiency, AWS certifications, Terraform and Infrastructure as Code, AWS Lambda/ECS/Fargate/RDS/Cognito/IAM/Step Functions, AWS security, MLOps, CI/CD, architecture governance, consulting/client-facing delivery, and international projects are nice to have
Benefits:
- Meal allowance: €10.20/day
- Flexible benefits plan
- Private medical insurance
- 22 days of annual leave, increasing every 3 years (up to 25 days)
- Continuous learning via KLX – Keyrus Learning Experience
- A collaborative, international, and human-centred work environment

















