← Back to All Openings

Senior Hybrid Retrieval & Evidence Integration Engineer

corpora-jobs-1778796293285-db9d41c6 - Frontier Development
Systems EngineerSenior1 position

Why This Role is Different

Frontier Development Role

You will architect and ship the evidence engine that keeps the debate honest. From vector‑search backends to policy‑driven query engines, you’ll turn raw knowledge into the fuel that powers every agent’s argument.

The Frontier Element

This role pushes the boundary of retrieval‑augmented reasoning by marrying LLMs with verifiable knowledge sources in a live, multi‑agent setting—an area where no existing product offers full end‑to‑end, low‑latency guarantees.

🔬

Project Context

Research Area

Agent‑Specific Evidence Retrieval and Query Policy

From: Hallucination Amplification in Multi‑Agent Debate

Why This Role is Critical

The HEAD framework’s core innovation is that every debating agent must autonomously fetch, vet, and prioritize evidence from curated knowledge bases. Building this retrieval backbone requires deep expertise in RAG, semantic search, and real‑time data pipelines.

What You Will Build

A production‑grade, low‑latency retrieval engine that supports confidence‑weighted queries, integrates domain ontologies, and streams verified snippets to the debate orchestrator.

🛠

Key Responsibilities

  • Design and implement the confidence‑weighted query policy that prioritizes high‑entropy, low‑certainty statements.
  • Build a scalable vector‑search infrastructure that ingests domain ontologies, peer‑reviewed literature, and sensor streams.
  • Develop a streaming API that delivers evidence snippets to agents with minimal latency and guarantees source verifiability.
  • Optimize token usage by pruning redundant evidence and integrating summarization triggers.
  • Collaborate with the Bayesian ensemble team to expose confidence scores and trust metrics for downstream aggregation.
🎯

Required Skills & Experience

Technical Must-Haves

Retrieval‑Augmented Generation (RAG) pipelines

Expert
Designing end‑to‑end systems that retrieve, rank, and inject evidence into LLM prompts.

Vector search and semantic indexing (FAISS, Milvus, Pinecone)

Expert
Building low‑latency, high‑throughput retrieval backends for millions of documents.

Knowledge graph construction and querying (Neo4j, RDF)

Advanced
Curating domain‑specific ontologies and linking evidence across modalities.

Python, Rust, or Go for high‑performance services

Expert
Implementing production‑grade microservices that interface with LLMs.

Distributed systems and container orchestration (Kubernetes, Docker)

Advanced
Deploying scalable, fault‑tolerant retrieval services.

Experience Requirements

  • 5+ years building RAG or semantic search systems for enterprise or research.
  • Track record of deploying retrieval‑augmented LLMs at scale (e.g., production RAG for a medical knowledge base).
  • Experience with real‑time sensor data ingestion and multimodal evidence pipelines.

Education

Master’s or PhD in Computer Science, Information Retrieval, or a related field.

Preferred Skills

  • Experience with InsightSwarm or similar evidence‑augmented debate frameworks.
  • Knowledge of medical ontologies (SNOMED, UMLS) or legal statutes for domain‑specific retrieval.
  • Familiarity with token‑budget optimization techniques used in LLM APIs.
🤝

You Will Thrive Here If...

  • Thrives in a high‑autonomy environment where rapid prototyping and shipping are valued.
  • Comfortable navigating ambiguity and iterating on novel research ideas.
  • Strong communicator who can translate complex retrieval concepts to non‑technical stakeholders.
📈

Impact & Growth

12-Month Impact

Within 12 months, deliver a retrieval engine that reduces hallucination amplification to <3% by ensuring every claim is backed by a cryptographically verifiable evidence snippet, while keeping token usage below 60% of baseline.

Growth Opportunity

Lead the evidence‑integration strategy across all high‑stakes product lines, shaping the next generation of verifiable AI reasoning systems.

Ready to Push the Boundaries?

If this sounds like the challenge you have been looking for, we want to hear from you. We value what you can build over where you have been.