Senior AI Engineer

About Burai  

Burai is an AI-driven productivity platform built around intelligent project management. At its core, Burai transforms how teams operate by seamlessly integrating AI Agents into existing workflows to automate repetitive processes. Through its unique “Digital Twin” technology, Burai learns how work actually happens, identifying patterns and surfacing opportunities for agentic automation.  

Working alongside employees, either in Office365 or Google Workspace, Burai actively monitors emails, joins meetings, and generates actionable summaries and tasks. This ensures that work moves forward efficiently, eliminating the overhead of manual coordination and follow-ups. The result is a smarter, faster, and more intuitive way to manage projects and drive productivity. 

What You’ll Do 

• Design and architect scalable AI systems, from data pipelines to inference endpoints, ensuring robust system design for multi-tenant SaaS environments. 

• Architect and build advanced AI agents for dynamic workflows and decision-making, leveraging RAG and agentic frameworks 

• Integrate and optimize LLMs for contextual understanding and reasoning, implementing sophisticated prompting strategies and evaluation frameworks. 

• Build and optimize machine learning pipelines, including feature engineering, model training, and continuous improvement of AI capabilities.  

• Design robust retrieval systems using vector embeddings.  

• Develop scalable APIs using FastAPI for high-performance integrations.  

• Deploy and manage AI services on
  Azure, ensuring reliability, security, and scalability.  

• Integrate Google ADK for enhanced AI capabilities in speech, vision, and data insights.  

• Build scalable, high-performing agent orchestrations in a SaaS multi-tenant environment.  

• Prototype and experiment with cutting-edge generative AI technologies.  

• Mentor engineers and establish best practices for AI/ML development and deployment.  

Requirements 

• Education:
  Bachelor’s or higher in Computer Science, Engineering, or related field.  

• Experience: 

• 5+ years in backend and AI engineering.  

• 3+ years working with LLMs at scale.  

• Technical Skills: 

• Strong system design and architecture skills, with ability to design scalable, maintainable solutions for complex technical challenges. 

• Expert-level Python programming with deep understanding of software engineering principles and design patterns. 

• Proven experience building production LLM applications, including RAG systems, agentic workflows, and prompt engineering at scale. 

• Expertise in FastAPI and RESTful API design and implementation 

• Strong proficiency in SQL for transactional and analytical workloads. 

• Experience with feature engineering and data preprocessing for machine learning models.  

• Familiarity with Node.js or Go is a plus.  

• AI/ML frameworks: LangChain, Hugging Face, PyTorch/TensorFlow.  

• Vector databases: Pinecone, Qdrant, Weaviate, Milvus, or similar.  

• Hands-on experience with containerization (Docker, Kubernetes) and deployment automation. 

• Cloud platform expertise: Azure required; experience with AWS or GCP highly valued. 

• Experience with CI/CD pipelines and containerization. 

• Integration with Google ADK.  

• Preferred experience with Model Context Protocol (MCP).  

• Proficiency in relational and NoSQL databases (PostgreSQL, MongoDB, Neo4j).  

• Soft Skills: Excellent communication, leadership, and problem-solving abilities.  

Nice to Have 

• Strong foundation in ML algorithms and theory, including supervised/unsupervised learning, neural networks, and optimization techniques. 

• Advanced generative AI experimentation.  

• Open-source contributions or AI-related publications.  

What We Offer 

• Competitive salary and equity options.  

• Autonomy to innovate and shape AI strategy.  

• Career growth through mentorship and learning budgets.  

• Local perks: paid lunches, MultiSport
  card, and top-tier equipment Apple or Microsoft.