AI & DATA ENGINEERING

Agentic AI Engineer

Build and evaluate agent-based applications for security workflows. You will work on tool integration, context management and reliable execution, with human review for sensitive actions.

Ho Chi Minh City, Vietnam (Hybrid)Full-Time4+ Years experience

What you’ll work on

Design and build agents that can plan, use tools and complete multi-step tasks in production security workflows.
Make agent workflows reliable with error handling, retries and human approval for sensitive actions.
Build tool-calling workflows that choose and configure security tools using the context available.
Develop prompts and agent workflows that can work across OpenAI, Google Vertex AI and Anthropic Claude.
Build and maintain the context layer that gives agents awareness of users, assets, past incidents, typical behavior, and environmental state.
Define practical evaluations for reliability, accuracy and safety, especially for exploit execution and incident response recommendations.
Collaborate with security engineers to translate offensive and defensive domain expertise into agent behavior, tool profiles, and decision logic.
Optimize for latency, cost, and token efficiency in production agent workloads.
Support on-premise deployments using self-hosted open-source models (DeepSeek, Llama) for air-gapped enterprise customers.

What you’ll bring

4+ years of software engineering experience with strong proficiency in Python.
1+ year of hands-on experience building LLM-powered agent systems (not chatbots, but agents that reason, plan, use tools, and take multi-step actions).
Deep working knowledge of at least one agentic framework: LangGraph, LangChain, CrewAI, AutoGen, or equivalent.
Experience with tool-calling / function-calling patterns, including dynamic tool selection and chaining.
Solid understanding of prompt engineering for complex reasoning tasks (chain-of-thought, ReAct, plan-and-execute patterns).
Experience integrating with multiple LLM providers (OpenAI, Anthropic, Google) and managing model-agnostic abstractions.
Experience building production systems that handle failures, retries, timeouts and monitoring.
Strong fundamentals in distributed systems, async programming, and API design.
Useful: experience in offensive security or defensive operations such as SOC, SIEM, detection engineering or incident response.
Plus: Familiarity with MITRE ATT&CK framework, Sigma rules, or detection-as-code practices.
Plus: Experience deploying and fine-tuning open-source LLMs (Llama, DeepSeek, Mistral) for on-premise or air-gapped environments.
Plus: Knowledge of graph databases (Neo4j) for modeling attack paths, or RAG pipelines and vector databases.

What’s on offer

Build agent systems for both offensive and defensive security products.
Help shape the product architecture and AI approach from the start.
Work with engineers who know both security and applied AI.
Competitive pay and a well-equipped workspace.

MORE OPEN ROLES

See where you could fit.

View all open roles