Our client, a telecommunications company in Denver, CO, is in need of a Network Telemetry/AI Solutions Architect for a 10-month contract-to-hire position. Working in a hybrid model, four days/week onsite, the Architect will work on defining the end-to-end system level architecture for the latency telemetry solution with emphasis on data ingestions, processing, and transport. This role will be developing AI/ML models and applying them to latency/jitter/packet loss data sets that are captured in the internet reliability program field trial in order to create decision criteria to identify network issues and improve customer QoE.
The Architect must have a working knowledge in system engineering, cloud platforms (e.g., AWS, Azure, GCP, etc.) and technologies (e.g., Kubernetes). This role demands deep experience in end-to-end system level architecture and engineering with emphasis on data ingestions, processing, and transport.
Core responsibilities include:
- Design and implement high-performance, scalable architectures for network systems, ensuring low-latency data processing and fault tolerance
- Collaborate on full-stack software development, emphasizing APIs, microservices, and cloud-native architectures
- Leverage machine learning (ML) and artificial intelligence (AI) techniques to analyze large-scale network telemetry for anomaly detection, predictive maintenance, and QoE optimization
- Optimize data ingestion, transformation, and transport across real-time streaming platforms (e.g., Apache Kafka, Pulsar, Flink) and batch processing frameworks (e.g., Apache Spark, Dask)
- Manage and integrate database technologies (SQL and NoSQL) for efficient storage and retrieval, including PostgreSQL, MySQL, Cassandra, and Redis, as well as columnar databases (ClickHouse, BigQuery, Apache Parquet) for analytical workloads.
- Define and implement RESTful APIs and GraphQL services, ensuring high availability and efficient communication between network management platforms and AI-driven automation layers
Required skills:
- 7+ years’ overall Engineering experience
- System Engineering & Architecture: Expertise in cloud-native architectures, container orchestration (e.g., Kubernetes, Docker Swarm), and edge computing
- Machine Learning & AI:
- Experience in developing supervised, unsupervised, and reinforcement learning models
- Proficiency in TensorFlow, PyTorch, Scikit-learn for ML model training and inference
- Experience deploying ML pipelines with MLflow, Kubeflow, or TensorFlow Serving
- Streaming & Data Processing:
- Familiarity with Kafka, RabbitMQ, Apache Pulsar for event-driven architectures
- Experience with ETL workflows using Apache Spark, Airflow, or Prefect
- Software Development & APIs:
- Proficient in Python, Go, Java, or Rust for backend development
- Experience designing RESTful APIs, gRPC services, and GraphQL endpoints
- Understanding of OAuth2, JWT, and API security best practices
- Networking & Telecommunications: Strong knowledge of SDN, NFV, network telemetry (gNMI, OpenConfig, SNMP, NetFlow) and protocol optimization for low-latency networking
- Excellent communication and collaboration skills
- Experience presenting at technical conference and writing research publications is a plus