Incora

Role Summary

We are looking for a Senior Data Scientist to lead the data intelligence layer of an AI-driven platform. This role focuses on extracting insights from structured and unstructured documents, building document processing and OCR pipelines, improving semantic retrieval systems, identifying information gaps in datasets, and maintaining high standards of data quality across end-to-end data workflows.
 

Key Responsibilities

• Design and improve OCR and document intelligence pipelines that convert complex PDFs and supporting files into structured, machine-readable data.
• Develop semantic retrieval workflows that identify relevant historical records and support recommendation systems based on similarity and contextual matching.
• Create data-driven methods to detect missing, incomplete, or inconsistent information within document-based datasets.
• Define and monitor data quality standards, validation rules, completeness checks, and anomaly detection mechanisms across data pipelines.
• Analyze structured and unstructured datasets to uncover patterns affecting operational performance, classification quality, and decision outcomes.
• Collaborate with machine learning engineers to prepare high-quality datasets for model training, validation, and iterative improvement.
• Develop labeling strategies, feature definitions, and dataset enhancement workflows for early-stage and production use cases.
• Evaluate the performance of retrieval systems, document extraction pipelines, and information coverage.
• Work closely with engineering and product teams to operationalize insights through dashboards, tools, and data-driven workflows.
• Communicate analytical findings, experiment results, and actionable insights clearly to technical and non-technical stakeholders.
   

Qualifications

• Bachelor’s or Master’s degree in Data Science, Computer Science, Statistics, Artificial Intelligence, or a related technical field.
• 5+ years of experience in data science, applied NLP, document intelligence, or analytics-focused roles. 
• Strong proficiency in Python and practical experience with data science libraries and NLP tooling. 
• Experience building document processing or OCR pipelines and working with semi-structured or noisy datasets.
• Strong understanding of embeddings, semantic search, retrieval evaluation, and similarity-based recommendation systems.
• Experience with data cleaning, validation, feature engineering, and dataset quality management.
• Ability to design experiments and translate analytical findings into product or model improvements.
• Strong SQL skills and solid analytical problem-solving abilities.
   

Nice to Have

• Experience working with AI systems in regulated or compliance-sensitive environments.
• Familiarity with multilingual NLP applications or systems that support multiple languages.
• Experience with vector databases or retrieval-augmented architectures.
• Exposure to annotation workflows and human-in-the-loop review processes.
• Experience building dashboards, defining operational KPIs, or supporting data-driven reporting.
  
  We offer:
• Flexible working schedule
• Fully remote work
• Compensation for medical, educational and sports activities
• Professional growth opportunities
• Internal knowledge-sharing talks
• Awesome team events and activities
• Paid vacation and sick leave

Role Summary

We are looking for a Senior ML Engineer who will be responsible for the end-to-end lifecycle of machine learning models, including design, training, evaluation, deployment, and ongoing optimization. In this role, the engineer will work on building and maintaining model ensembles, defining inference logic, establishing retraining workflows, monitoring model performance and drift, and integrating ML solutions into production systems that support real-time decision processes.

The platform follows a hybrid architecture where deterministic rule-based logic is applied first, and more complex scenarios are routed to a machine learning layer for deeper analysis.
 

Key Responsibilities:

• Design, train, fine-tune, and optimize machine learning models used for risk estimation, classification tasks, and automated decision support.
• Develop and maintain ensemble strategies that combine outputs from multiple models, including confidence-based routing and prediction aggregation.
• Build and manage retraining pipelines leveraging synthetic, curated, and eventually production-scale datasets to continuously improve model performance.
• Define evaluation methodologies, performance thresholds, fallback strategies, and human-in-the-loop review triggers for low-confidence predictions.
• Collaborate with backend and product teams to integrate model inference into real-time services and scalable production APIs.
• Improve model reliability, interpretability, and operational performance across early-stage and production workflows.
• Implement monitoring systems to track model drift, prediction quality, system latency, and conditions that trigger retraining.
• Explore and evaluate alternative domain-adapted foundation models when appropriate.
• Ensure traceability and auditability of model predictions while adhering to security, privacy, and deployment standards.
• Contribute to system architecture, MLOps practices, and deployment standards for machine learning solutions in secure cloud or on-premise environments.
   

What We’re Looking For:

• Bachelor’s or Master’s degree in Computer Science, Machine Learning, Artificial Intelligence, Data Science, or a related technical field.
• 5+ years of practical experience building and deploying machine learning solutions in production environments.
• Strong proficiency in Python and experience with modern machine learning frameworks such as PyTorch, TensorFlow, or similar tools.
• Solid understanding of core ML concepts including supervised learning, classification, ranking methods, model calibration, and evaluation techniques.
• Experience adapting and fine-tuning domain-oriented models, as well as working with multi-model or ensemble-based approaches.
• Hands-on experience developing ML pipelines covering training, validation, deployment, and iterative retraining.
• Familiarity with integrating ML systems into API-driven services, as well as working with containers, CI/CD pipelines, and model serving infrastructure.
• Experience with experiment tracking, model version control, and monitoring model performance in production.
• Ability to work effectively with incomplete, evolving, or partially labeled datasets in real-world environments.
   

Nice to Have:

• Experience working with AI systems in regulated or compliance-sensitive environments.
• Familiarity with multilingual machine learning use cases or models designed to support multiple languages.
• Experience applying model explainability techniques, confidence estimation, and human-in-the-loop review workflows.
• Exposure to vector search, semantic retrieval methods, or document understanding pipelines.
• Experience building or operating ML solutions in privacy-sensitive environments with strict data protection requirements.
  
  We offer:
• Flexible working schedule
• Fully remote work
• Compensation for medical, educational and sports activities
• Professional growth opportunities
• Internal knowledge-sharing talks
• Awesome team events and activities
• Paid vacation and sick leave