Lead Agent Systems Engineer - Production-Grade LLM Agents

GlobalLogic Inc.; Polska; Sur place; PLN 180 000 - 250 000; Plein temps

Avantages offerts par ce poste

Diversity and inclusion

Comprehensive benefits

Career development

Relocation options

Résumé du poste

GlobalLogic collaborates with a leading global threat intelligence platform to design an enterprise‑scale, Human‑in‑the‑Loop AI agent platform. The project aims to accelerate analyst decision‑making by augmenting complex workflows with generative and agentic AI systems.

Location: Open to candidates based in Poland, Romania, or Ukraine. The role requires hands‑on experience in production LLM apps, distributed systems design, and technical leadership of 4–8 engineers.

Qualifications

• 8+ 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.

Responsabilités

• 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.

Connaissances

8+ years software engineering

LLM applications in production

LangGraph experience

Vertex AI Agent Engine

asynchronous Python

distributed systems design

technical lead

Outils

LangGraph

Vertex AI Agent Engine

MCP

OpenTelemetry

GCP (Cloud Run, Pub/Sub, BigQuery)

Description du poste

GlobalLogic collaborates with a leading global threat intelligence platform to design an enterprise‑scale, Human‑in‑the‑Loop AI agent platform. The project aims to accelerate analyst decision‑making by augmenting complex workflows with generative and agentic AI systems.

Location: Open to candidates based in Poland, Romania, or Ukraine. The role requires hands‑on experience in production LLM apps, distributed systems design, and technical leadership of 4–8 engineers.