Data Science ML/Gen AI Engineer (Mid-Level)- Orbit
Irth Solutions2 months ago
Remote, IndiaMid Level / Senior
Responsibilities
- Build medallion architecture pipelines in Databricks and implement data quality checks, validation gates, data contracts, lineage, governance, PII protection, and access controls.
- Prototype, evaluate, and productionize machine learning and GenAI solutions for forecasting, anomaly detection, NLP, RAG, LLM assistants, copilots, and predictive analytics.
- Package and manage models with Unity Catalog, and design batch and streaming inference architectures with monitoring, SLAs, documentation, and operational runbooks.
- Build production workflows, jobs, and notebooks as infrastructure/assets-as-code using Databricks Asset Bundles and implement CI/CD with GitHub Actions.
- Develop reliable and observable data and ML workloads, including monitoring, alerting, SLO management, incident tracking through Jira, and FinOps optimization.
- Contribute semantic models and governed business metrics for consumption through Power BI and Databricks AI/BI.
- Implement secure ML and data architectures using RBAC, ABAC, private networking, key-management services, and policy-as-code.
- Support compliance, auditability, access reviews, retention controls, security reviews, and disaster recovery testing.
Requirements
- Requires 3–6 years of experience in Data Science, Machine Learning, or ML Engineering and a record of taking models from development through production.
- Requires strong Python, SQL, and Spark/PySpark programming and data skills.
- Requires hands-on Databricks experience with Delta Lake, Unity Catalog, Databricks SQL, Jobs and Workflows, and medallion architecture.
- Requires knowledge of feature engineering, model training and selection, evaluation and validation, model monitoring, data-quality monitoring, and drift detection.
- Requires practical GenAI/LLM experience with prompt engineering, RAG, vector databases or stores, LLM evaluation, AI safety, guardrails, and latency, scalability, and cost tradeoffs.
- Requires CI/CD experience for data and ML workloads, including GitHub Actions, Databricks Asset Bundles, environment promotion, and secrets and configuration management.
- Requires experience with data contracts, schema governance, automated testing and expectations, validation, and quarantine or error-handling workflows.
- Requires understanding of PII protection, RBAC/ABAC, data residency, policy-as-code, and related security and compliance practices.
- Requires clear technical documentation skills, including architecture decision records, runbooks, experiment reports, and operational documentation.
- Preferred qualifications include Azure, AWS, geospatial analytics, streaming and real-time data, MLflow, Unity Catalog Model Serving, data and ML observability, FinOps, disaster recovery, resilience, and relevant infrastructure or asset-integrity industry experience.
- Nice-to-have experience includes predictive or risk-scoring models, asset-integrity failure prediction, anomaly detection, time-series forecasting, GIS-based feature engineering, and translating ML outputs into operational or customer-facing insights.
Benefits
- Competitive compensation based on experience and qualifications.
- Medical, dental, and vision insurance.
- 401(k) plan with company match.
- Generous paid time off and company-paid holidays.
- Remote work-from-home opportunities are available depending on role and business needs.
- Additional on-call compensation is available for eligible shifts.
Tech Stack
Categories
Data EngineeringML Engineering
About Irth Solutions
Irth Solutions builds cloud-based software used by utilities and other critical-infrastructure operators to manage 811 one-call tickets, land rights, risk, and mobile field work, with reporting and analytics. Its products are sold as SaaS and include AI-driven risk modeling for pipeline asset integrity. Founded in 1985 and headquartered in Columbus, Ohio, the company is privately held and owned by Gauge Capital.