Senior AI Engineer (AWS Bedrock)
New
A
Automat-itGenerative AI
Remote from UkraineFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- English (written and spoken)
- Required Skills
- AWSPythonGenerative AI
Requirements
- Have strong hands-on experience building and deploying AI/GenAI systems in production.
- Have strong AWS experience beyond model invocation, including infrastructure, IAM, serverless services, networking, storage, monitoring, and production deployments using Amazon Bedrock.
- Have practical experience building RAG systems, including retrieval logic, vector databases, and output quality improvements.
- Understand modern LLM ecosystems, including commercial and open-source models, trade-offs, deployment options, and production use cases.
- Have strong Python skills and a good understanding of backend system design.
- Have experience designing multi-agent systems or complex orchestration workflows.
- Have experience with vector databases such as OpenSearch, pgVector, or Pinecone.
- Be comfortable working in fast-moving environments with short project cycles.
- Be able to work directly with clients and cross-functional teams and explain technical decisions, limitations, and trade-offs in spoken and written English.
- Experience with Amazon Bedrock Knowledge Bases, AgentCore, Agents, AWS Strands, or MCP is an advantage.
- Experience selecting, evaluating, and optimizing LLMs for quality, latency, and cost is an advantage.
- Experience with Infrastructure as Code, Docker, Kubernetes, and CI/CD pipelines is an advantage.
Responsibilities
- Build and deliver production-ready GenAI systems on AWS, including RAG systems, intelligent document processing, voice AI, and LLM-powered services.
- Design and implement AI agents using Amazon Bedrock AgentCore, AWS Strands, MCP, and orchestration frameworks.
- Work with Solution Architects, DevOps, and customer teams to turn discovery workshops, ideas, and POCs into production systems.
- Evaluate and select LLMs based on accuracy, latency, cost, and customer requirements.
- Build reusable AI components and deployment patterns for customer projects.
- Deploy, monitor, and improve production ML/LLM systems for performance, cost, and reliability.
- Use AWS services including Bedrock, OpenSearch, Lambda, S3, DynamoDB, SageMaker, and CloudWatch.
- Adapt existing ML or GenAI code for production environments.
- Improve retrieval performance, output consistency, and evaluation approaches.
- Own projects as the main engineer in a fast-paced, project-based environment.
View Full Description & ApplyYou'll be redirected to the employer's site
