Senior AI Engineer: Hybrid RAG & HITL Threat Intel

GlobalLogic Inc.; Kraków; On-site; PLN 240,000 - 420,000; Full time

Benefits offered by this job

Comprehensive benefits

Relocation options

Learning & Development

Diversity & Inclusion

Career development

Job summary

GlobalLogic is partnering with a leading threat intelligence platform to design an enterprise-scale HITL AI agent platform, aimed at accelerating expert analyst decision-making with cutting-edge generative and agentic AI systems.

The role focuses on building hybrid retrieval over enterprise sources, creating a precedent store with human decisions, delivering report generation with source attribution, and developing automated evaluation frameworks.

Qualifications

• 5+ years of engineering experience, including 2+ years on production RAG or search systems.
• Experience with embeddings and vector databases.
• Experience with LLM evaluation methods and tooling.
• Strong Python proficiency from prototype to production.
• Background in information retrieval or NLP research.
• Experience with Vertex AI Search and BigQuery; in-context learning optimization.
• Experience with structured report generation and citation grounding.

Responsibilities

• Build hybrid retrieval over enterprise sources (vector and keyword search), with reranking and permission-aware filtering.
• Build the precedent store: index decision points with human decisions and rewards, and retrieve the right examples at runtime.
• Deliver report generation and explanation layers with source attribution.
• Build automated evaluation: golden datasets, LLM-as-judge, regression suites, and A/B tests of few-shot strategies.
• Apply the dynamic few-shot approach to the LLM stage of alert triage.

Skills

Python

RAG/LLM systems

IR/NLP research

Vector databases

LLM evaluation tooling

Production engineering

Tools

Vertex AI Search

BigQuery

pgvector

DSPy

Job description

GlobalLogic is partnering with a leading threat intelligence platform to design an enterprise-scale HITL AI agent platform, aimed at accelerating expert analyst decision-making with cutting-edge generative and agentic AI systems.

The role focuses on building hybrid retrieval over enterprise sources, creating a precedent store with human decisions, delivering report generation with source attribution, and developing automated evaluation frameworks.