Duties and Responsibilities :
- Provides deep technical expertisein the aspects of cloud infrastructuredesign and APIdevelopment for the business environments.
- Bridgesthe gap between data scientists and software engineers, enabling the efficient and reliable delivery of ML - powered solutions
- Ensures solutions are well designedwith maintainability / ease of integration and testing across multipleplatforms.
- Possess strong proficiency in development and testing practices common to the industry
Summary of Principal Job Responsibility & Specific Job Duties and Responsibilities :
Working closely with data scientists, ML engineers, and other stakeholders to deploy ML modelsSetting up and maintaining cloud and edge infrastructure for MIL models deploymentDesign, implement and maintain scalable infrastructure for ML workloadsGood verbal and written communication skillsCollaborative and orientedAcademic Qualification(s) :
Bachelor's degree in computer science, Engineering or related subject and / or equivalent formal training or work experience
Work Experience / Skills Requirement(s) :
Cloud Infrastructure & KubernetesMinimum 2 years of hands-on experience managing cloud infrastructure (e.g. AWS,GCP,Azure) in a production environment
Hands-on experience with Kubernetes for container orchestration, scaling and deployment of ML servicesFamiliar with Helm charts, ConfigMaps, Secret and autoscaling strategiesAPI Development & Messaging IntegrationProficient in building and maintaining RESTful or gRPC APIs for ML inference and data services
Experience in message queue integration such as RabbitMQ or ZeroMQ for asyncronous communication, job queuing or real-time model inference pipelinesSystem Design, Database & Software ArchitectureProven experience working with relational databases (RDBMS) such as Microsoft SQL Server and PostgreSQL.
Proficient in schema design, writing complex queries, stored procedures, indexing strategies, and query optimization.Hands-on experience with vector search and embedding-based retrieval systems.Practical knowledge using FAISS, LanceDB, or Qdrant for building similarity search or semantic search pipelines.Understanding of vector indexing strategies (e.g., HNSW, IVF), embedding dimensionality management, and integration with model inference pipelines.Programming LanguagesDemonstrated expertise in building scalable and maintainable API services using Python frameworks such as Flask, FastAPI, or Litestar.
Fluent in HTML, CSS, and JavaScript for building simple web-based dashboards and monitoring interfaces.Experience with Go, C++, or Rust is a strong plus, especially for performance-critical or low-latency inference applications.Edge AI DeploymentExperience in integrating models using NCNN, MNN, or ONNX Runtime Mobile on mobile and edge devices.
Familiarity with quantization, model optimization, and mobile inference profiling tools.MLOps & ToolingExperience with Docker / Podman, CI / CD pipelines, Git, and ML lifecycle tools such as MLflow, Airflow, or Kubeflow.Exposure to model versioning, A / B testing, and automated re-training workflows.Monitoring & LoggingAbility to set up monitoring (e.g., Prometheus, Grafana) and logging (e.g., ELK stack, Loki) to track model performance and system health.
Soft Skills & CollaborationStrong analytical and troubleshooting skills.
Able to work closely with data scientists, backend engineers, and DevOps to deploy and maintain reliable ML systems.Excellent communication and documentation habits.#J-18808-Ljbffr
