Senior AI Engineer (Information Retrieval)

TL;DR

Senior AI Engineer (Information Retrieval): Building the context management layer, search systems, and data integrations that enable AI agents to access and reason over enterprise information with an accent on semantic retrieval, data pipelines, and scalable agent infrastructure. Focus on designing hybrid lexical and vector search, optimizing relevance and latency, and delivering reliable production systems for enterprise customers.

Location: Remote within European time zones

Company

hirify.global builds agentic labor infrastructure that enables humans and AI agents to operate together as a unified workforce for governments and global enterprises.

What you will do

• Design and build scalable lexical, semantic, and hybrid search and retrieval systems.
• Develop connectors for SaaS platforms, data warehouses, document stores, and APIs.
• Build ingestion, transformation, and indexing pipelines for customer data.
• Integrate LLM providers and agent frameworks to deliver context-aware capabilities.
• Own projects from architecture and implementation through deployment and maintenance.
• Optimize retrieval quality, latency, and cost while collaborating with product and AI teams.

Requirements

• 10+ years of engineering experience and a degree in computer science, engineering, or a related field.
• Strong Python skills and willingness to work with additional languages as the stack evolves.
• Experience with at least one major cloud platform, such as GCP, AWS, or Azure.
• Experience with Docker and Kubernetes and the ability to operate across the stack without dedicated DevOps support.
• Experience working in a fast-paced startup environment and owning major projects independently.
• Ability to work remotely within European time zones.

Nice to have

• Experience with enterprise SaaS integrations, source connectors, or production systems serving enterprise customers.
• Hands-on experience with Elasticsearch, vector databases, embeddings, semantic search, RAG, chunking, re-ranking, and hybrid retrieval.
• Experience with data pipelines, ETL/ELT workflows, and data warehouses such as Snowflake, BigQuery, Databricks, or Redshift.
• Production experience with LLM APIs and agent frameworks such as LangChain or LlamaIndex.
• Knowledge of data governance, access control, multi-tenant architectures, or open-source search and retrieval projects.

Culture & Benefits

• High-ownership environment focused on speed, creativity, efficiency, and quality.
• Opportunity to work on agentic AI infrastructure operating at enterprise scale.
• Collaboration with experienced research and product professionals from leading technology companies.
• Remote work aligned with European time zones.