Data Engineer - LLM Pipeline & Data Infrastructure

We're building an AI-powered conversational system for drive-thru automation. As our Data Engineer, you'll design and implement the infrastructure that powers our multi-stage LLM pipeline, from data capture to processing, model training, and deployment.

Tasks

• Build scalable real-time data pipelines for audio processing, LLM interactions, and model training
• Design comprehensive data storage solutions across object storage, NoSQL, and analytical databases
• Implement data quality management with filtering, normalization, and enrichment capabilities
• Create automated processes for data preparation, model evaluation, and continuous improvement
• Develop observability systems with monitoring, alerting, and performance dashboards
• Establish data security and compliance protocols, including privacy protection measures
• Build resilient data systems with error recovery, backup, and integrity verification

Requirements

What You'll Need

• Experience designing data pipelines for AI/ML applications
• Expertise with Apache Airflow for workflow orchestration
• Strong knowledge of Apache Spark for large-scale data processing
• Experience with Apache Kafka for real-time event streaming
• Proficiency with object storage systems (S3/MinIO) and database technologies (Cassandra/ScyllaDB, ClickHouse)
• Understanding of monitoring tools (OpenTelemetry) and observability platforms
• Experience implementing data security and compliance measures
• Advanced Python programming skills

Preferred Experience

• Audio data processing and conversational AI systems
• LLM training and fine-tuning pipelines
• Data quality frameworks (Great Expectations) and versioning tools (LakeFS, DVC)
• Kubernetes for container orchestration
• Multi-region deployment and distributed systems

Benefits

• Build cutting-edge conversational AI systems with real-world impact
• Work with modern, open-source technology stack
• Help shape the future of automated customer service
• Competitive compensation and flexible work arrangements

If you're passionate about building robust data systems for AI applications and excited by complex real-time data challenges, we'd love to talk.

Vox AI is a voice-powered operating system built specifically for restaurants, transforming traditional drive-thru experiences into streamlined, personalized interactions. With roots in multilingual Europe, our solution integrates effortlessly into existing restaurant systems, enhancing order accuracy, speed, and customer satisfaction. Trusted by global partners like HME, Oracle, and NCR, Vox AI’s adaptive technology handles diverse accents and challenging environments, ensuring seamless communication in any location.