The Position

My OPSWAT Portal is OPSWAT's one stop hub for customers and partners. We provide a central place to manage licenses, access support, download products, track training, and navigate OPSWAT cloud services securely. It brings essential tools together in one place so customers and partners can get started quickly and stay productive. 

This role is for an engineer who would rather own the model than rely on someone else: you build and integrate AI/LLM features into our platform based on product and business requirements.  

You will be responsible for continuously improving the AI’s accuracy, latency, cost efficiency, security, and reliability. 

What You Will Be Doing: 

• Develop and integrate RAG, AI agents, recommendation/search systems, and AI-powered automation workflows.  
• Build and maintain data ingestion, embedding, retrieval, and evaluation pipelines.  
• Collaborate with the Engineering Team (Developers & QA) to design, build, test, and deliver AI features.  
• Collaborate with the DevOps Team to deploy, monitor, and optimize our self-hosted LLMs. 
• Build and maintain evaluation gates for every LLM change and make it something the team trusts more than its own intuition. 

What We Need from You: 

• At least 3+ years of relevant experience in AI/ML engineering. 
• Strong Python, including building data pipelines for training datasets. 
• Good understanding of Prompt Engineering, RAG, Embeddings, Vector Databases, Tool Calling, AI Agents, and LLM Evaluation.  
• Experience with Rest APIs, SQL/No-SQL databases, Docker, Git, and CI/CD.  
• Ability to debug, evaluate, and validate AI systems in real-world production environments. 
• Experience with LLM serving, APIs (e.g. OpenAI, Anthropic, Azure OpenAI, …), inference (e.g. vLLM, Ollama), including quantization and the memory / latency / quality trade-off on constrained hardware. 
• Familiarity with tool-calling / agent-based LLM applications. 
• Ability to design and run model evaluations for non-deterministic systems: you can name a metric you designed and the number you moved. 
• Strong verbal and written communication skills in English: the language of the team, the docs, and the prompts. 
• Self-motivated, adaptable, and comfortable owning a track in a fast-paced, team-oriented environment. 

It Would Be Nice If You Had: 

• Experience fine-tuning open-weight LLMs  
• Experience with agent frameworks  
• Awareness of LLM security risks: prompt injection, data leakage, misuse. 
• Compact models deployed on-premises, offline, or resource-constrained environments. 
• Evaluation tooling for LLM systems: LLM-as-judge, regression suites, human review loops. 
• Cybersecurity concepts, or experience building components of a security product

#LI-onsite