← Back to Projects

ClinicalSearch

Evidence Retrieval AI

Multi-agent evidence retrieval system with supervisor-routed specialist delegation. Multi-stage retrieval pipeline across hybrid vector search, LLM-scored relevance ranking, and quality-weighted synthesis with inline evidence metadata. Retraction-filtered retrieval with citation traversal and consensus detection across specialist outputs.

PythonAWSPineconeEmbeddingsMulti-AgentRAG

About

Multi-agent evidence retrieval system with domain-specialized agents. A supervisor routes queries by LLM reasoning to relevant specialists; each runs a multi-stage pipeline — hybrid vector search, external API fallback, retraction filtering, LLM reranking, and quality-weighted sort. Evidence quality metadata propagates inline; consensus detection identifies agreement, debate, and emerging findings across specialist outputs.

The Problem

Evidence synthesis across heterogeneous domain-specific corpora requires concurrent retrieval from multiple specialized sources, quality assessment at retrieval time, and attribution-preserving synthesis. Single-model retrieval flattens domain distinction and lacks the multi-source aggregation needed to surface contradictions.

The Approach

Supervisor-mediated specialist delegation routes each query by LLM reasoning. Each specialist runs a multi-stage retrieval pipeline with hybrid semantic search, external API calls with local databases, citation traversal, and LLM-based relevance scoring that drops low-quality chunks before synthesis. Consensus detection operates across specialist outputs to surface agreement, debate, and emerging findings.

Tech Stack

  • Frontend: FastAPI with SSE streaming · Frontend included
  • Backend: Python, AWS, Pinecone, OpenAI Embeddings and more...
  • AI/ML: Strands Agent Framework, Pinecone, PubMed API, Custom Orchestration, Citation Pipeline

Apply

Apply by April 30, 2026

Apply Now →

You'll learn

  • Multi-Agent RAG
  • Hybrid Vector Search
  • LLM Reranking
  • Citation Systems
  • AWS
  • Agentic Frameworks

Open roles

Applied AI Engineer

Build and extend RAG evaluation pipelines with self-consistency verification. Optimize retrieval accuracy for medical literature and clinical guidelines.

Apply →

Backend Engineer

Design search infrastructure, document ingestion APIs, and caching layers. Build scalable query processing with async architecture.

Apply →

Frontend Engineer

Build the clinician-facing search interface — result rendering, source highlighting, confidence indicators. Focus on speed and clarity for time-pressed users.

Apply →

Data Engineer

Parse PDFs, medical records, and research papers into structured searchable formats. Build extraction pipelines for tables, citations, and clinical metadata.

Apply →

AI Researcher

Evaluate retrieval quality across medical domains. Design benchmark datasets, run ablation studies, and research domain-specific embedding and ranking strategies. Contribute to evaluation methodology publications.

Apply →

DevOps / MLOps

Cloud deployment, latency optimization, search index management. Monitor retrieval quality in production.

Apply →