Data Scientist

Drive production-ready data science for manufacturing at Hadrian by predicting cycle time, cost, tool wear/life, quality/yield, and triage risk ahead of production runs.

Responsibilities

• Build and ship production models for cycle time, tool life, quality, and demand using calibrated uncertainty (quantile, conformal, or Bayesian) instead of point estimates alone.
• Predict outcomes directly from geometry by engineering features and developing geometric/graph models for cycle time, cost, DFM, tolerance risk, and triage probability.
• Create a part and operation embedding layer representing parts via geometry, material, tolerances, and route; perform similarity retrieval and transfer behavior to cold-start new parts.
• Validate with honest backtesting that respects time ordering and prevents part-family leakage; justify model choice (deep vs classical) per problem.
• Own model lifecycle end to end on the platform: reproducible training, serving, monitoring, and retraining in partnership with ML Platform and Data Engineering.
• Close the loop in production by detecting drift and quality anomalies so predictions improve as new data arrives.
• Translate predictions into business decisions for quoting, scheduling, capacity, and DFM; design experiments/A-B tests to measure impact; document results and hand off to operations.

Requirements

• Experience with forecasting and prediction on messy manufacturing data with honest uncertainty.
• Proficiency in representation learning and embeddings, including similarity/retrieval and transfer or few-shot approaches for limited, sparse data.
• Ability to build shipping deep learning solutions in PyTorch and apply judgment on when deep learning is or is not appropriate.
• Strong classical ML and statistics including GBMs, Bayesian/hierarchical, survival, and causal methods.
• Demonstrated validation rigor: backtesting, leakage control (time and part-family), and calibration.
• Strong Python skills for turning complex processes into features and models that can be consumed by operators and downstream systems.
• Experience deploying and monitoring models, with pipelines and drift considered from the start.
• Comfort working with limited, high-value data and borrowing strength across related cases.

Technologies

• PyTorch
• quantile
• conformal
• Bayesian
• GBMs
• Python
• PyTorch Geometric
• CAD
• B-rep
• GNNs
• ANN
• IoT
• A/B tests

Benefits

• Medical, dental, vision, and life insurance plans for employees
• 401k
• Relocation support may be provided for certain situations, based on business need
• Flexible vacation policy
• Equity

Compensation

• Target salary range: USD 170,000 - 300,000 per yearly (actual range may vary based on experience)
• Pay position within the range is based on factors including relevant education, qualifications, certifications, experience, skills, geographic location, performance, and business or organizational needs

ITAR Requirements

• To conform to U.S. Government space technology export regulations (including ITAR), candidates must be a U.S. citizen, lawful permanent resident of the U.S., protected individual as defined by 8 U.S.C. 1324b(a)(3), or eligible to obtain required authorizations from the U.S. Department of State.

Use of AI in Hiring

• Hadrian uses AI-assisted tools in recruiting and hiring to help the team work more efficiently.
• AI tools support the team and are not used to make hiring decisions; human evaluation and decisions are used.
• If an interview will be recorded, you will be notified in advance and may opt out at any time without impact on candidacy.
• Candidate data processed through these tools is subject to the same protections described in Hadrian’s Privacy Policy.