We are looking for a Data Scientist with 2–4 years of hands-on experience to lead and drive data-driven initiatives across Smart Node’s ecosystem. In this role, you will not only build advanced statistical and machine learning models, but also lead end-to-end development, mentor junior engineers, and productionize scalable data products. You will work closely with cross-functional business units—including Sales, Operations, Supply Chain, and Customer Experience—as well as firmware, cloud, and hardware teams to transform raw IoT telemetry, ERP workflows, and user interactions into scalable, production-grade intelligence. --- ## Key Responsibilities ### Technical Leadership & Team Guidance Lead Data Projects: Act as the technical point of contact for data science initiatives, owning solutions from problem formulation to production deployment.

Mentorship & Code Quality: Code-review work, champion modular coding standards, design robust system architectures, and mentor junior data scientists/analysts.

Cross-Functional Ownership: Collaborate directly with business leaders (Sales, HR, Finance, Operations) to translate high-level business goals into technical roadmaps. ### End-to-End ML & AI Solutions Demand & Inventory Optimization: Architecture and end-to-end implementation of time-series predictive demand models to streamline inventory and reduce stockouts.

Sales Intelligence: Build, deploy, and monitor lead scoring and churn prediction models to maximize sales conversion rates and customer lifetime value (LTV).

Predictive Maintenance & IoT Telemetry:



Build high-reliability failure forecasting models using streaming IoT device data (e.g., heartbeat logs, MQTT payloads) in collaboration with hardware/cloud teams.

NLP & Generative AI Systems: Design and integrate production-grade LLM applications (e.g., automated support, operational text classification) using modern API/RAG frameworks. ### Productionization, MLOps & Architecture Model Deployment: Deploy ML models into production via scalable microservices (FastAPI/Flask) with real-time monitoring for model drift and performance latency.

Pipeline Integration: Partner with cloud/data engineers to build and maintain robust ETL pipelines integrating mobile app events, cloud infrastructures, and ERP databases.

BI & Real-Time Analytics: Oversee the design of high-throughput real-time dashboards to track hardware health, operational bottlenecks, and core enterprise KPIs. --- ## Required Skills ### Core Data Science & Engineering Experience: 2–4 years of demonstrated experience building, deploying, and maintaining production ML models in a fast-paced environment.

Advanced Python: Deep proficiency in production-level Python (OOP, design patterns, profiling) and core libraries (Pandas, NumPy, Scikit-learn, XGBoost, LightGBM).

API Development & Microservices:



Strong experience building and deploying robust REST APIs using FastAPI, Flask, or Django using Docker containers.

Data Engineering & SQL: Advanced SQL skills for data modeling, window functions, and handling large-scale unstructured/structured datasets. ### Machine Learning & AI Deep Learning Frameworks: Practical experience using PyTorch or TensorFlow for production tasks.

NLP & LLM Applications: Hands-on experience with modern NLP workflows, Hugging Face transformers, and integrating Generative AI APIs / vector databases into production systems.

Computer Vision (Practical): Understanding of vision pipelines (OpenCV, YOLO, ResNet) for edge or cloud image/video analysis. ### MLOps & Production Tools MLOps Foundations: Familiarity with model tracking, registry, and CI/CD tools (MLflow, DVC, Git, Docker). --- ## Positive to Have Edge AI & Embedded Systems: Hands-on experience with Edge AI deployment (TensorFlow Lite, ONNX Runtime) for low-latency IoT or mobile edge execution.

IoT Protocols & Streaming: Experience with IoT communication patterns (MQTT, WebSockets, Kafka, Kinesis) and stream processing.

Voice Interfaces: Experience developing or integrating voice AI systems (Speech-to-Text, Whisper, Alexa/Google Assistant integrations).

Orchestration: Experience with pipeline orchestrators like Airflow, Prefect, or Dagster.

Cloud Infrastructure: Experience deploying models on cloud environments (AWS e.g., EC2, S3, SageMaker, Lambda OR GCP / Azure).

- BI Tools: Hands-on ability to build and guide team output using tools like Power BI, Tableau, or Apache Superset

📌 Vadodara, Gujarat - Data Scientist
🏢 Smart Node
📍 Vadodara