Company Description
ThreatXIntel is a cybersecurity startup focused on protecting businesses of all sizes from evolving digital threats. Our experienced team specializes in cloud security, web and mobile security testing, cloud assessments, and DevSecOps, offering tailored solutions to address unique client needs. We are committed to providing affordable, high-quality services, enabling businesses to safeguard their digital assets. Using a proactive approach, we continuously monitor and test digital environments to mitigate vulnerabilities before exploitation. At ThreatXIntel, our mission is to empower organizations with reliable cybersecurity solutions, fostering their growth and success in a secure digital landscape.
Role Description
We are seeking a Senior Generative AI Engineer with strong expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and enterprise-grade GenAI system development.
The consultant will design, build, and deploy end-to-end Generative AI solutions across text, image, audio, and multimodal applications. This role focuses on production deployment, optimization, and scalable AI architecture design.
Key Responsibilities
- Design and build end-to-end Generative AI pipelines including data collection, preprocessing, training, evaluation, and deployment
- Develop applications using generative models such as GPT, LLaMA, Claude, Stable Diffusion, and similar architectures
- Implement enterprise RAG pipelines using vector databases and embedding frameworks
- Integrate LLMs and multimodal AI systems using LangChain, LlamaIndex, Hugging Face, and API-based frameworks
- Optimize model inference performance, latency, and operational cost
- Develop intelligent AI-driven applications in collaboration with product, data science, and engineering teams
- Implement prompt engineering strategies and embedding pipelines
- Deploy models using Docker, Kubernetes, and CI/CD pipelines
- Work with cloud platforms such as Azure, AWS, or GCP
- Utilize Azure AI services such as Azure AI Foundry and AI Search where applicable
Required Technical Skills
Generative AI and LLMs
- Hands-on experience with GPT, LLaMA, Claude, Mistral, or similar LLMs
- Practical experience implementing RAG architectures
- Experience with LangChain, LlamaIndex, and Hugging Face Transformers
- Strong understanding of prompt engineering and embeddings
Vector Search and Retrieval
- Experience with FAISS, Pinecone, Weaviate, Milvus, or similar vector databases
Programming and ML
- Strong Python programming skills
- Experience with PyTorch or TensorFlow
Cloud and MLOps
- Experience with Azure, AWS, or GCP
- Containerization using Docker and Kubernetes
- API development and CI/CD pipeline integration
Multimodal AI
- Exposure to image generation models such as Stable Diffusion or DALLE
- Experience with multimodal systems combining text, vision, and speech
