Hi, I'm |

Software Development Engineer - Data

Building scalable systems, optimizing ML/NLP pipelines, and crafting robust backend architectures.

About Me

Anirban Sinha
Pune, India
+91 8967644102
anirbansinha191@gmail.com

Who I Am

I'm a Software Development Engineer specializing in data engineering, backend development, and machine learning. With a strong foundation in computer science and a passion for building scalable systems, I've dedicated my career to creating efficient, reliable software solutions.

At Bajaj Finserv Health, I've focused on optimizing NLP pipelines, implementing asynchronous architectures, and fine-tuning Elasticsearch for improved search relevance. My work has significantly reduced latency, accelerated model training, and enhanced overall system performance.

I'm particularly passionate about the intersection of data engineering and machine learning, where I leverage my expertise to build robust backend architectures that can handle large-scale data processing while maintaining high performance and reliability.

When I'm not coding, I enjoy mentoring junior developers, exploring new technologies, and contributing to open-source projects that align with my interests in data science and backend development.

Skills & Expertise

Programming Languages
Python
JavaScript
TypeScript
Frameworks
NestJS
Node.js
Streamlit
Databases
MySQL
Elasticsearch
MongoDB
Message Queues & Tools
Kafka
Azure Service Bus
ELK Stack
Docker
Git
Data Science & DevOps
Pandas
NumPy
Apache Airflow
Kubernetes
CI/CD
Specialties
Machine Learning
NLP
Back-end Development
Data Analysis
Microservices

Featured Projects

Intent and Entity Recognition Engine
BERT
Elasticsearch
FastAPI
NLP
Python

Engineered an intent recognition system integrating Elasticsearch for named entity recognition (NER) and query analysis. Finetuned a BERT-based Transformer model for intent classification, improving accuracy and response efficiency. Engineered a high-performance backend with FastAPI, achieving a 20ms response time for real-time predictions.

Doctor Ranking Framework
NestJS
Elasticsearch
Kafka
TypeScript
Redis

Developed an efficient doctor ranking and allocation framework that improved appointment bookings by 15% and reduced patient wait times by 20 minutes on average. Implemented advanced algorithms to match patients with the most suitable healthcare providers based on multiple factors.

Asynchronous Processing Pipeline
NestJS
Kafka
Redis
Microservices
TypeScript

Migrated synchronous processes to an asynchronous architecture using NestJS, Kafka, and Redis, decreasing latency by 60%, processing 2 million transactions daily and reducing server costs by 15%.

Work Experience

Nov 2024 - Present
Software Development Engineer
Bajaj Finserv HealthPune, India
  • Migrated synchronous processes to an asynchronous architecture using NestJS, Kafka, and Redis; decreased latency by 60%, processing 2 million transactions daily and reducing server costs by 15%.
  • Revamped the NLP pipeline by optimizing data preprocessing and parameter tuning, accelerating model training by 90% and improving query response times threefold, resulting in higher customer satisfaction scores.
  • Optimized Elasticsearch ranking algorithms by fine-tuning relevance scoring and query expansion, improving search accuracy by 40% and providing deeper insights into user engagement patterns, leading to more relevant and efficient search results.
  • Configured and maintained Elasticsearch clusters, ensuring 99% up-time for mission-critical services.
  • Implemented real-time stored procedures and data pipeline failure alerts, enabling faster acknowledgment and resolution of production failures.
  • Mentored a team of 3 interns in designing a doctor slots framework, increasing appointment bookings by 15% and reducing patient wait times by 20 minutes on average.
Jan 2023 - Oct 2024
Associate Software Development Engineer
Bajaj Finserv HealthPune, India
  • Defined high-throughput data pipelines for processing and analyzing large-scale datasets, reducing data latency by 60%.
  • Streamlined data ingestion pipelines by automating data validation with Python scripts, achieving 40% faster processing and enhancing data quality reporting for stakeholders.
  • Introduced custom NLP models to improve query interpretation, leading to a 25% increase in search relevance.
  • Collaborated with engineers, analysts, and product managers to develop a pricing and cancellation system, increasing booking efficiency by 25% and reducing cancellation losses by 40%.
Jan 2022 - Dec 2022
Data Science Intern
HighRadiusBhubaneswar, India
  • Automated data pipelines using Python, streamlining data preparation and processing.
  • Incorporated predictive analytics for a B2B application, improving forecast accuracy in predicting repayment dates.
May 2021 - Dec 2021
R&D Intern - PRISM
Samsung IndiaIndia
  • Refined Softmax Regression using gradient descent, achieving 92% accuracy on a dataset of 100,000 handwritten images.

Education

Bachelor of Technology in Computer Science and Engineering
Kalinga Institute of Industrial Technology, Bhubaneswar, India
May 2019 - Aug 2023
CGPA: 9.2

Completed a comprehensive computer science curriculum with a focus on data structures, algorithms, database management, and software engineering principles. Participated in various hackathons and technical competitions, enhancing practical skills alongside theoretical knowledge.

Achievements

Sharp Shark Award
October 2024

Recognized for developing an efficient Doctor Ranking and Allocation Framework that improved appointment bookings by 15% and reduced patient wait times.

Sharp Shark Award
April 2024

Awarded for enhancing back-end system efficiency and eliminating 5XX errors, significantly improving system reliability and user experience.

Get In Touch

Contact Information
Feel free to reach out through any of these channels
Send Me a Message
I'll get back to you as soon as possible