Data Engineer

To Apply Please fill the form: https://lnkd.in/g4KwqECF

Company Description

NovaIA offers an AI-powered voice assistant tool designed to support human agents in real time. Particularly tailored for real estate agencies, the assistant can make calls, follow up with leads, filter prospects, and schedule appointments. Key features include real-time agent support and appointment management automation. The assistant listens in on conversations, providing live guidance, data, or suggestions, and seamlessly handles follow-ups and meeting setups through voice interactions.

Role Description

Data Engineer

Key Responsibilites:

• Design & Implement Pipelines

  – Build robust, low-latency pipelines for real-time STT input, NLP processing, and TTS output.

• Ingestion Systems

  – Develop scalable ingestion for audio logs, model artifacts, and interaction metadata.

• Stream Management

  – Manage message queues and streaming data for efficient voice call routing and real-time responses.

• Caching & Prefetching

  – Optimize caching layers and prefetching logic for pre-recorded response fragments.

• ETL/ELT Workflows

  – Create workflows for downstream analytics, monitoring, and continuous feedback loops.

• Session Memory

  – Develop and manage session memory stores for dynamic context handling.

• Data Governance

  – Ensure data versioning, schema consistency, and lineage tracking.

• Cost Optimization

  – Collaborate on token usage optimization and infrastructure cost reporting.

Core Skills

• Data Pipeline Orchestration

  : Apache Airflow, Prefect, Luigi, dbt

• Stream Processing

  : Kafka, Apache Flink, Redis Streams, RabbitMQ

• Programming

  : Python, SQL; familiarity with Java/Scala is a plus

• Cloud Platforms

  : AWS (Kinesis, S3, Lambda), GCP (Pub/Sub, BigQuery), or Azure equivalents

• Storage Systems

  : PostgreSQL, DynamoDB, Parquet, Snowflake, Delta Lake

• Data Quality & Observability

  : Schema validation, Great Expectations, monitoring tools

• Audio Data Handling

  : Experience with transcription logs, metadata tagging, media storage

• Version Control & CI/CD for Data

  : Git, DVC, automated testing workflows

Preferred / Bonus Skills

• Familiarity with ML model pipelines and experiment tracking
• Experience with real-time ETL optimization and low-latency microservices
• Knowledge of vector databases (FAISS, Chroma, Pinecone)
• Experience with WebRTC, SIP, or other real-time audio systems
• Understanding of data governance and compliance (PII masking, audit trails)