Coderoad Data Scientist at CodeRoad develops machine learning models and applies AI, NLP, and LLM techniques. Builds data pipelines and translates data into business insights.
Responsibilities
Develop & Improve Machine Learning Models: Build, test, and refine machine learning and statistical models to identify anomalies, forecast costs, analyze shipping rates, and classify invoices. Evaluate model performance and contribute to improving predictive accuracy.
Apply AI, NLP & LLM Techniques: Explore and apply Natural Language Processing (NLP), embeddings, and Large Language Models (LLMs) to extract meaningful insights from unstructured supply chain documents, logistics contracts, and other business data.
Build & Maintain Data Pipelines: Collaborate with AI and software engineers to prepare datasets, develop feature engineering workflows, and support model deployment, monitoring, and automated retraining.
Conduct Exploratory & Scenario Analysis: Clean, transform, and analyze transactional datasets to identify patterns, evaluate shipping trends, compare carrier rates, and support cost optimization and contract negotiation decisions.
Translate Data into Business Insights: Use SQL, statistical analysis, and data visualization to communicate findings clearly and turn complex data into actionable recommendations for business stakeholders.
Maintain Data Quality & Model Performance: Implement data quality checks, validate analytical results, monitor model performance, and follow established security and governance standards across cloud data environments.
Explore & Adopt Emerging AI Tools: Proactively experiment with AI tools, libraries, and techniques to improve analytical workflows, automate repetitive tasks, accelerate experimentation, and identify new ways to solve business problems.
Relevant Experience: 1–3 years of professional experience in data science, machine learning, applied statistics, or a related analytical role, with hands-on experience working on real-world datasets and analytical projects.
Python & Data Science Fundamentals: Practical experience with Python and common data science libraries such as pandas, NumPy, and scikit-learn. Familiarity with statsmodels or similar statistical tools is a plus.
SQL & Database Knowledge: Experience writing SQL queries to retrieve, transform, and analyze data from relational databases. Familiarity with Microsoft SQL Server or PostgreSQL is preferred.
Machine Learning & AI: A solid understanding of machine learning concepts, including regression, classification, clustering, and time series forecasting. Exposure to NLP, embeddings, and LLMs is highly desirable, particularly through hands-on projects or practical applications.
Cloud & Analytics Tools: Familiarity with cloud-based machine learning or AI platforms, preferably Azure Machine Learning or Azure AI Foundry. Experience with Power BI, Tableau, or Python visualization libraries is an advantage.
