As a Senior AI Engineer, you will play a central role in shaping the core AI infrastructure of a growing SaaS platform. You'll architect and implement intelligent, agent-driven workflows that interact deeply with customer knowledge systems, ensuring robust, scalable, and secure performance in production.
What You'll Do
- Design and deploy an autonomous agent framework paired with a contextual knowledge graph to streamline complex workflows across enterprise data sources
- Lead the full lifecycle of AI systems—from concept to deployment—focusing on LLM integration, context management, and multi-model strategies
- Develop comprehensive evaluation frameworks including offline benchmarks, live metrics, A/B testing, and human-in-the-loop validation
- Implement and maintain LLMOps practices such as model monitoring, incident response, performance tuning, and cost controls for latency and token usage
- Build security safeguards against prompt injection, unauthorized data access, and improper tool use, ensuring safe execution in sensitive environments
- Define engineering best practices, reusable components, and documentation that elevate team velocity and code consistency
- Drive alignment across technical initiatives, translating ambiguous challenges into clear roadmaps and deliverables
Requirements
- Proven track record delivering AI/ML systems to production, with strong fundamentals in software design, testing, reliability, and API development
- Deep familiarity with LLM application patterns including context engineering, vector search, structured output generation, and prompt strategies
- Experience building evaluation and monitoring pipelines for AI models in live environments
- Proficiency with cloud platforms (specifically Azure), containerization, CI/CD pipelines, and observability tools
- Excellent communication skills in English, with experience turning complex problems into actionable plans in collaborative, cross-functional settings
Preferred Qualifications
- Background in optimizing model inference through techniques like caching, batching, routing, or quantization
- Hands-on experience fine-tuning or serving open-source LLMs
- Experience developing internal AI platforms, including tools for prompt management, version control, or evaluation frameworks
Technical Stack
Python, Vue.js, Next.js, C#, ASP.NET, Azure, GitHub, Linear, Claude Code, Cursor, Copilot
