Back
Tier-1 brand and mid-level role attract applicants, but niche retrieval/agent specialization limits pool.
Specialized IR, vector DB, and agent-platform expertise limits cross-industry transferability.
Explicit 3–10 years plus specific vector DB, RAG, Python, and AWS requirements enforce strict filtering.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design and operate scalable vector databases and hybrid retrieval systems integrating semantic search with graph context and business logic.
Build and maintain RAG pipelines for structured/unstructured data contextualization and implement agent connectivity through MCP-based tool discovery and orchestration.
Develop observability tools and feedback loops for key agent performance metrics; optimize cloud AWS infrastructure for cost, security, and performance.
Bachelor’s or Master’s degree in Computer Science, Data Science, Engineering, or a related field.
3 to 10 years of experience in information retrieval, vector databases, or agent platform engineering.
Proficiency with at least one vector database in production (e.g., Pinecone, Weaviate, Qdrant) and experience building RAG pipelines.
Strong Python 3.10+ backend engineering skills with CI/CD pipeline ownership; familiarity with AWS cloud infrastructure and provisioning.
Experienced in hybrid retrieval systems combining vector semantic search with graph-based context and business logic filters.
Hands-on with MCP or equivalent agent-tool interoperability frameworks, skill registries, and capability discovery implementations.
Skilled in observability and performance optimization using OpenTelemetry, Prometheus/Grafana, distributed tracing, and AWS services for scalable, cost-efficient deployments.