Senior Data Scientist

Title / Designation – Data Science Engineer / Data scientist

Experience Required Overall: 8-10 years

Domain Experience – Manufacturing 4-5 Years

Duration- 12 months + Extension possible

Base Location - Easton, Pennsylvania

Work Model – Onsite – Hybrid who are local or willing to relocate / Remote with travel across USA also is an option

Number of Internal interviews with Implementation– 1 (Technical)

Client Interviews - 2 (1 Technical & 1 Functional Cultural fit)

Mode of Interviews – Virtual

Tentative start date – ASAP

Job Description:

- 8–10 years of overall
data science experience required along with
4-5 years working in manufacturing domain.
- Hands-on experience in shop floor operations, production planning, and systems including MES, SCADA, and ERP.
- Proficient in industrial protocols (OPC-UA, MQTT, Modbus) with ability to bridge OT/IT systems for real-time data extraction.
- Applied experience with OEE, Six Sigma, SPC, and lean methodologies to drive measurable gains in yield, uptime, and efficiency.
- Data Engineering Skilled in building scalable cloud data pipelines for high-volume manufacturing and IoT data using Spark, Kafka, Airflow, and Delta Lake.
- Strong SQL and Python proficiency with hands-on experience in medallion/lakehouse architectures on Databricks, Snowflake, AWS, or Azure.
- Data Science Proven track record building and deploying ML models for predictive maintenance, anomaly detection, demand forecasting, and root cause analysis.
- Proficient in scikit-learn, TensorFlow, or PyTorch with experience moving models from prototype to production in industrial environments.
- Strong communicator — able to translate complex model outputs into clear, actionable recommendations for operations and executive stakeholders.
- Solid grounding in statistical methods — time series, regression, clustering, and hypothesis testing applied to manufacturing quality problems.
- Experience designing A/B experiments and simulations to validate process changes and quantify business impact before full deployment.