About the Role

We are building the next-generation automated health-insurance claims processing platform, leveraging AI/ML, deep learning, NLP, OCR, and LLM powered intelligence. As a Data Scientist, you will contribute to the design, development, deployment, and optimization of AI models that power large-scale claims decisioning across multiple regions. This is a hands-on technical role where you will work alongside senior data scientists, gain exposure to end-to-end ML pipelines, and grow your expertise in a fast-paced, mission-critical environment.

Key Responsibilities

Model Development, Deployment & Production Support

- Contribute to the development, training, and validation of ML models used in automated health-claims processing.
- Assist in building and maintaining end-to-end machine learning pipelines including data ingestion, feature engineering, and model evaluation.
- Experiment with classical ML models (tree-based, linear, clustering) and modern approaches NLP, transformers) under senior guidance.
- Support monitoring of model performance and data quality in production environments. Implement and test model improvements based on feedback and performance metrics.

Build Efficient, Scalable & High-Accuracy Models

- Optimize models for accuracy, latency, memory footprint, and infrastructure cost.
- Implement model compression, distillation, and quantization when required to meet SLAs.
- Ensure solutions perform reliably across heterogeneous real-world datasets and regions. Implement

End-to-End ML Pipelines

- Implement automated ML pipelines covering structured,



unstructured, and document based data. Build feature engineering, model training, validation, and retraining workflows.
- Implement CI/CD for ML, model versioning, and automated retraining strategies.
- Work closely with engineering teams to operationalize ML using MLOps best practices.

Experience in AI Techniques

- Hands-on experience with classical ML models including tree-based models, linear models, clustering, and anomaly detection.
- Experience with deep learning architectures such as CNNs, RNNs, and Transformers.
- Strong background in NLP and LLM-based solutions for extraction, summarization, classification, and claim interpretation.
- Ability to evaluate and select the most appropriate technique for each problem.

Solid Technical Acumen

- Deep understanding of data structures, machine learning algorithms, and modern AI architectures.
- Proficiency in Python, ML frameworks such as PyTorch and TensorFlow, and cloud platforms including AWS, GCP, or Azure.
- Familiarity with distributed systems, microservices, APIs, and containerized deployments.
- Experience building scalable data pipelines and feature stores.
- Define data quality standards,



metadata tracking, and experiment management practices.
- Write high-quality, production-ready Python code using frameworks such as PyTorch, Hugging Face, LangChain, or Ollama.
- Conduct rigorous model validation, interpretability analysis, and bias detection.

Collaboration & Communication

- Collaborate with senior data scientists, ML engineers, and product teams to deliver solutions Document experiments, findings, and model decisions clearly
- Participate in code reviews, technical discussions, and knowledge-sharing sessions
- Proactively communicate progress, blockers, and learnings to the team

Required Qualifications

- Engineering degree in Computer Science, Statistics, Mathematics, or a related field
- 2 to 5 years of experience in data science or ML (including internships or academic projects)
- Solid understanding of ML fundamentals: supervised/unsupervised learning, model evaluation, overfitting
- Hands-on experience with Python and key libraries: scikit-learn, pandas, NumPy
- Hand-on experience with LLMs, RAG and Agentic Pipelines
- Familiarity with at least one deep learning framework: PyTorch or TensorFlow
- Basic knowledge of NLP: tokenization, embeddings, text classification
- Working knowledge of SQL for data querying and manipulation
- Exposure to cloud platforms AWS, GCP, or Azure) and version control (Git)
- Strong analytical thinking and problem-solving skills
- Eagerness to learn, take ownership, and grow in a fast-paced environment

📌 Data Scientist (Bengaluru)
🏢 IHX - A Perfios
📍 Bengaluru