AI Engineer AWS & LLM Production Systems

Location: Wrocław
Contract Type: 6 Months

Job Status: Hybrid

• Work on production AI systems using Amazon Bedrock and LLMs
• Maintain and optimise cloud infrastructure across AWS services
• Join a team working with cutting-edge AI and automation technologies
• Gain hands-on experience with LangChain frameworks and vector indexing
• Contract opportunity based in Wrocław

Our client is a technology-focused organisation working at the intersection of AI cloud computing and data analytics. They specialise in building and maintaining production-ready AI systems that handle conversational analytics and predictive support. The team works with modern AWS infrastructure and cutting-edge LLM technologies to deliver scalable solutions. This is an opportunity to join a forward-thinking environment where youll work with the latest AI frameworks and cloud technologies.

Theyre looking for an AI Engineer to join their team in Wrocław on a contract basis. This role offers the chance to work hands-on with production AI systems maintaining and optimising LLM configurations cloud infrastructure and data pipelines.

As an AI Engineer youll play a key role in maintaining and supporting production AI systems built on AWS infrastructure. Youll work across the full technology stack from LLM prompt debugging and conversational analytics to cloud infrastructure management and CI/CD pipelines. Your work will directly impact the performance and reliability of AI-powered systems ensuring smooth operations and continuous improvement of machine learning pipelines and search schemas.

• Maintain Python codebases using pandas NumPy and Excel Power Query scripting
• Configure and debug Amazon Bedrock LLM implementations and conversational analytics
• Work with LangChain or similar frameworks to maintain vector indices
• Optimise Amazon Athena views and manage Amazon S3 bucket structures
• Validate Amazon SageMaker model pipeline loops for predictive support
• Maintain Amazon OpenSearch and Athena schema optimisation and indexing scripts
• Manage AWS Serverless setups IAM user roles VPC subnets and storage
• Support Docker containers Git branch management and pipeline monitoring
• Debug REST APIs and handle JSON data payloads
• Monitor AWS schedulers and maintain code environment stability

• 4-6 years of relevant experience in AI engineering or cloud development
• Strong Python programming skills particularly with pandas and NumPy
• Hands-on experience with AWS services including Bedrock Athena S3 and SageMaker
• Knowledge of LLM configuration prompt engineering and conversational AI
• Experience with LangChain or similar AI frameworks
• Understanding of vector index maintenance and search schema optimisation
• Proficiency in AWS cloud infrastructure management and DevOps practices
• Familiarity with Docker Git and CI/CD pipeline tools
• Experience debugging REST APIs and working with JSON data structures
• Ability to manage IAM roles VPC subnets and serverless architectures

While specific benefits havent been disclosed youll work in a technology-driven environment focused on AI innovation and cloud computing. Youll collaborate with specialists in machine learning data engineering and cloud architecture gaining exposure to production-scale AI systems and modern AWS infrastructure.

To apply for this role please submit your CV using the form below or email