Staff Retrieval Engineer (AI)

TL;DR

Staff Retrieval Engineer (AI): Designing and optimizing large-scale search systems and retrieval infrastructure for legal documents with an accent on blending traditional IR with modern vector search and AI-driven approaches. Focus on building next-generation search capabilities, integrating LLM-augmented retrieval, and driving continuous improvement in retrieval quality across multi-tenant cloud-native environments.

Location: Hybrid, based in Illinois, USA

Salary: $174,000–$262,000

Company

hirify.global is a stable, cloud-native product organization investing heavily in platform engineering and AI-enabled search architectures for the legal tech domain.

What you will do

• Architect, design, and optimize large-scale retrieval infrastructure, including indexing pipelines.
• Lead the evolution from traditional inverted-index search to hybrid retrieval systems.
• Collaborate with AI/ML engineers to integrate LLM-augmented retrieval and re-ranking into production search flows.
• Partner with platform teams to ensure retrieval systems are observable, performant, and cost-efficient.
• Establish benchmarking and evaluation frameworks for retrieval quality and drive continuous improvement.
• Mentor engineers across teams, lead design reviews, and champion technical excellence in search and retrieval.

Requirements

• 8+ years of professional experience in software engineering with a significant focus on information retrieval systems at scale.
• Deep expertise in search engines and frameworks (Elasticsearch, Solr, Lucene, Vespa, OpenSearch).
• Strong knowledge of retrieval models (BM25, vector similarity, hybrid retrieval, learning-to-rank).
• Proven experience with distributed systems and storage, including index sharding and replication.
• Strong programming skills in Java, C++, C#, Python, or Go, with system-level performance optimization.
• Proficiency with data processing frameworks (Spark, Flink, Kafka, Kinesis) for indexing and retrieval pipelines and experience with cloud-native environments (Azure, AWS, GCP), Docker, and Kubernetes.

Nice to have

• Experience integrating vector databases (Pinecone, Weaviate, Milvus, FAISS, pgvector) into production systems.
• Familiarity with large-scale machine learning for ranking, embeddings, and transformers.
• Experience with knowledge graph technologies (Neo4j, JanusGraph, TigerGraph, RDF, SPARQL, GraphQL).
• Familiarity with legal tech, e-discovery, or enterprise SaaS search challenges.

Culture & Benefits

• Comprehensive health, dental, and vision plans.
• Parental leave for primary and secondary caregivers.
• Flexible hybrid work arrangements.
• Unlimited time off and two week-long company breaks per year.
• Long-term incentive program and training investment program.