Overview

We are seeking a strong Machine Learning Engineer + Data Scientist hybrid to design, build, and productionize ML-driven observability solutions on top of large-scale session data (RUM, logs, WebRTC, clickstreams). The role focuses on behavioral inference, anomaly detection, multimodal signal fusion, and scalable ML systems to reduce MTTR/MTTD and improve user experience insights.

Key Responsibilities

• Design and implement ML-driven observability solutions.
• Focus on behavioral inference and anomaly detection.
• Work with multimodal signal fusion and scalable ML systems.
• Reduce MTTR/MTTD and improve user experience insights.

Required Skills

• Core ML & DS
  • Strong foundation in:
    • Supervised & unsupervised learning
    • Anomaly detection
    • Time-series modeling (Prophet/ARIMA/Deep Learning)
    • NLP (Transformers, BERT variants)
    • GenAI – LLM, RAG, Agentic
  • Experience with multimodal ML systems
• Engineering & Systems
  • Strong Python skills
  • Experience with:
    • PySpark / Spark / distributed data processing
    • Streaming systems (Kafka)
    • APIs & microservices
  • Ability to handle high-scale event data pipelines
• Modeling Techniques
  • Clustering (hierarchical, KMeans, density-based)
  • Classification (XGBoost, tree-based models)
  • Feature extraction (TF-IDF, embeddings)
• MLOps & Deployment
  • Experience with:
    • ML pipelines (Kubeflow)
    • Docker/Kubernetes
    • Model versioning & monitoring

Good to Have

• Experience with observability/RUM tools
• Knowledge of WebRTC/audio signal processing
• Exposure to LLMs, RAG, and prompt engineering
• Understanding of frontend performance metrics (LCP, INP, CLS)

Experience

8+ years in Data Science / Machine Learning Engineering