Lead Agent Engineer

GlobalLogic takes an opportunity to partner with a leading global threat intelligence platform to design and deliver an enterprise-scale, Human-in-the-Loop (HITL) AI agent platform. The initiative centers on accelerating expert analyst decision-making by augmenting high-complexity threat intelligence workflows with cutting-edge generative and agentic AI systems.

ONLY FOR CANDIDATES LOCATED IN POLAND, ROMANIA, OR UKRAINE

Job Description
Essential qualifications
7+ years of software engineering, including 2+ years building LLM applications in production.
Production agent systems built with LangGraph, Google ADK / Vertex AI Agent Engine or custom orchestration.
Hands-on MCP experience, especially the client side: tool routing, authentication and transports (HTTP/SSE).
Expert asynchronous Python and strong distributed-system design.
Has taken agents from prototype to production and measured their quality with real users.
Desirable qualifications
A deep-research or multi-step retrieval agent built and shipped.
A2A protocol, OpenTelemetry tracing for LLM systems, and GCP (Cloud Run, Pub/Sub, BigQuery).
Previous technical lead of a team of 48 engineers.
Job Responsibilities
Key responsibilities
Design and build the Shared Foundation:
agent runtime and orchestration
MCP client and tool layer
state and memory
tracing
evaluation hooks.
Instrument every agent decision point (situation, options, choice and later human reward) as the basis for feedback learning.
Build the deep research agents: planning, iterative search across internal and external sources, synthesis, citation grounding and context management.
Set engineering standards, lead code review and mentor the team.
Work with the Solution Architect on security, multi-tenancy and enterprise integration.