AI Engineer (RAG, LLM, Python)

3 Lý do để gia nhập công ty

• Product company with global reputation in security
• Competitive compensation package & salary reviews
• Full social insurance & extra health-care program

Mô tả công việc

The Position

We are building an AI-powered autonomous vulnerability management platform that goes beyond traditional scanning and reporting. 

Our vision shifts from reactive to predictive, providing a true endpoint-to-vulnerability visibility, and replacing human-intensive manual processes with intelligent AI agents.

Join our team and help build the future of vulnerability management and cybersecurity automation.

In this role, you will provide cybersecurity domain expertise to guide AI model development, validate autonomous security decisions, and ensure our platform meets enterprise security requirements. You will also bridge the gap between cutting-edge AI and practical cybersecurity operations.

What You Will Be Doing:

• Design and implement multi-agent AI systems using frameworks like CrewAI, LangChain, AutoGen or similar.
• Develop predictive models (LSTM, transformers) for vulnerability exploitation forecasting.
• Build RAG (Retrieval Augmented Generation) pipelines for vulnerability intelligence synthesis.
• Fine-tune large language models on cybersecurity datasets with hundreds of thousands vulnerability identifiers (CVE).
• Implement vector databases for semantic vulnerability search.
• Create AI-powered autonomous patching agents with validation and rollback capabilities.
• Optimize model performance for both cloud and local deployment scenarios.
• Collaborate with security researchers to validate AI model outputs.

Yêu cầu công việc

What We Need From You:

• From 3 years experience in AI/ML engineering, preferably in cybersecurity or enterprise software.
• Deep expertise in LLMs (GPT, Claude, Llama) and their practical applications.
• Proficiency in Python AI ecosystem: PyTorch/TensorFlow, Transformers, LangChain, LlamaIndex etc.
• Experience with multi-agent systems and autonomous AI workflows.
• Knowledge of vector databases and embeddings for semantic search.
• Understanding of RAG architectures and prompt engineering.
• Familiarity with MLOps tools: MLflow, Weights & Biases, or similar.
• Good background in time-series analysis and predictive modeling.
• Experience deploying AI models in production environments.

It Would Be Nice If You Had:

• Cybersecurity domain knowledge: vulnerability assessment, threat intelligence.
• Experience with local AI deployment (Ollama, vLLM) and air-gapped environments.
• Knowledge of cybersecurity frameworks: MITRE ATT&CK, CVSS, CVE databases.
• Background in fine-tuning models on domain-specific datasets.
• Experience with reinforcement learning for autonomous decision-making.
• Familiarity with security-focused AI models (SecurityBERT, etc.).
• Open source contributions to AI/ML projects.

Tại sao bạn sẽ yêu thích làm việc tại đây

• Meaningful work with passionate colleagues
• International working environment in global leading cyber security product company
• Attractive compensation, regular assessments, and salary reviews
• 13-month bonus & performance bonus
• 100% salary, full insurances on probationary period
• Extra-health care program (PVI) for employee and family members
• 15 to 20+ paid day off per year
• Recognition best employees awards quarterly, yearly and special President Club award every year
• Stock options for employees
• Attractive benefits for team activities (team building, team outing, sport, trade union activities)
• Nice open office on the top of a building in District 3 with full of accessories for active recreation, sport, fruits, coffee, and tea.