AI Retrieval & Agent Platform Engineer
Siemens AGMatch Score
Against your primary resumeLogin to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Protocol Intelligence
Data-driven signals on your job's competitivenessLog in to see why each signal reads the way it does.
Job Description
Structured overview of role & requirementsAbout This Role
Design and evolve enterprise-scale retrieval and agent platform architectures for scalable AI solutions, focusing on RAG pipelines and vector search systems.
Build, deploy, and optimize production-grade vector databases and agent orchestration frameworks integrating multiple enterprise data sources and tools.
Ensure platform performance, observability, security, and cost optimization by deploying cloud-native services on AWS with CI/CD and infrastructure-as-code practices.
Minimum Requirements
Bachelor's or master’s degree in Computer Science, Data Science, Engineering, or related discipline.
3 to 10 years of experience in retrieval systems, vector databases, search platforms, GenAI engineering, or agent-platform development.
Hands-on production experience with at least one vector database (e.g., Pinecone, Weaviate, Qdrant, Milvus) and strong Python backend development skills.
Experience with AWS cloud services (including Bedrock, AgentCore, Lambda, ECS, EKS), containerization (Docker, Kubernetes), and CI/CD pipelines (GitLab).
Ideal Candidate Profile
Experienced in designing and operating Retrieval-Augmented Generation (RAG) architectures with hybrid retrieval techniques combining vector search, graph intelligence, and metadata filtering.
Familiar with graph technologies (Neo4j, AWS Neptune) and skilled in integrating multi-hop agent frameworks for contextualized AI decision-making.
Comfortable working across cross-functional global teams to define platform standards, observability practices, and enterprise-grade AI tool integrations.