Harsh Joshi profile photo 1 on Tal

Harsh Joshi

Machine Learning Engineer | Google Cloud Certified Professional Data Engineer | Production ML Systems, MLOps & Data Engineering | GCP | NLP | Computer Vision | BigQuery | Vertex AI

Pune Division

3+ years of work experience

CitiusTech
Oct 20241 yr 11 mosPresent

Pune District

• Designed and deployed machine learning models for healthcare data analytics, including predictive risk-stratification models and NLP-based clinical text classification pipelines, improving prediction accuracy by 15%. • Built and maintained scalable ETL data pipelines on Google Cloud Platform (BigQuery, Dataflow, Cloud Storage) to process large-scale healthcare datasets while adhering to HIPAA-compliant data handling standards. • Collaborated with data engineers, and product managers to translate business requirements into production-ready ML solutions, reducing model development cycle time by 10%. • Optimized model inference performance, reducing latency by 12% through quantization and batching strategies. • Addeddata quality checks and alert-friendly logging for ML pipelines to improve diagnosability and reduce recurring deployment issues.
Spark Minda
Aug 20231 yr 3 mosOct 2024

Pune District

• Built and trained deep learning models for automated quality inspection on manufacturing lines, reducing manual inspection effort by 25% and false-positive defect rates by 15%. • Designed and implemented data pipelines to collect, clean, and preprocess sensor and IoT data from embedded automotive systems for model training and evaluation. • Optimized and deployed lightweight CNN models on edge devices for real-time inference, reducing on-device la tency while preserving model accuracy. • Collaborated with embedded systems and hardware teams to integrate ML models into production automotive electronics. • Worked on production troubleshooting and model iteration using feedback from real-world telemetry and defect analysis.

Harsh’s AI Stack

claude code
claude code
claude
claude
codex
codex
deepseek
deepseek
gemini
gemini
hugging face
hugging face

Education

Pimpri Chinchwad Education Trust'S. Pimpri Chinchwad College Of Engineering

Bachelor of Engineering - BE, Electronics and Telecommunication

Pimpri Chinchwad Education Trust'S. Pimpri Chinchwad College Of Engineering

20194 yrs2023

12th

B.S. Memorial School, Aburoad

20181 yr2019

Join Harsh and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Harsh Joshi on Tal

Headline

Machine Learning Engineer | Google Cloud Certified Professional Data Engineer | Production ML Systems, MLOps & Data Engineering | GCP | NLP | Computer Vision | BigQuery | Vertex AI

About

AI/ML Engineer with 3+ years of experience building and deploying production-grade machine learning, data engineering, and computer vision solutions across healthcare and automotive domains. Currently, I design and develop scalable ML systems, cloud-native data pipelines, and analytics solutions on Google Cloud Platform (GCP). My experience spans the full machine learning lifecycle—from data collection and feature engineering to model training, deployment, monitoring, and continuous improvement. I have hands-on expertise in Python, SQL, TensorFlow, PyTorch, Scikit-learn, BigQuery, Dataflow, Vertex AI, Apache Spark, and MLOps practices. I enjoy solving complex business problems through data-driven approaches and building reliable systems that deliver measurable impact in production environments. Key areas of experience: • Machine Learning & Deep Learning • Data Engineering & ETL Pipelines • MLOps & Model Deployment • Google Cloud Platform (GCP) • Computer Vision & NLP • Predictive Analytics & Time-Series Modeling • A/B Testing & Statistical Analysis • Production Monitoring & Reliability Some of my work includes developing predictive healthcare analytics solutions, NLP-based clinical text classification systems, automated visual inspection models for manufacturing, and edge-deployed computer vision applications. I am also a Google Cloud Certified Professional Data Engineer and an IEEE-published researcher in biometric identification. I am particularly interested in scalable ML platforms, experimentation systems, statistical validation, and building trustworthy AI solutions that create real-world impact. Always open to connecting with professionals working in AI, Machine Learning, Data Engineering, MLOps, and Cloud Technologies.

Location

Pune Division

AI stack

claude code

claude

codex

deepseek

gemini

hugging face

Work experience

Software Engineering Machine Learning Engineer at CitiusTech, Oct 2024 - Present · 1 yr 11 mos, Pune District, • Designed and deployed machine learning models for healthcare data analytics, including predictive risk-stratification models and NLP-based clinical text classification pipelines, improving prediction accuracy by 15%. • Built and maintained scalable ETL data pipelines on Google Cloud Platform (BigQuery, Dataflow, Cloud Storage) to process large-scale healthcare datasets while adhering to HIPAA-compliant data handling standards. • Collaborated with data engineers, and product managers to translate business requirements into production-ready ML solutions, reducing model development cycle time by 10%. • Optimized model inference performance, reducing latency by 12% through quantization and batching strategies. • Addeddata quality checks and alert-friendly logging for ML pipelines to improve diagnosability and reduce recurring deployment issues.

Engineer – Data Analytics & AI/ML at Spark Minda, Aug 2023 - Oct 2024 · 1 yr 3 mos, Pune District, • Built and trained deep learning models for automated quality inspection on manufacturing lines, reducing manual inspection effort by 25% and false-positive defect rates by 15%. • Designed and implemented data pipelines to collect, clean, and preprocess sensor and IoT data from embedded automotive systems for model training and evaluation. • Optimized and deployed lightweight CNN models on edge devices for real-time inference, reducing on-device la tency while preserving model accuracy. • Collaborated with embedded systems and hardware teams to integrate ML models into production automotive electronics. • Worked on production troubleshooting and model iteration using feedback from real-world telemetry and defect analysis.

Education

Bachelor of Engineering - BE, Electronics and Telecommunication, Pimpri Chinchwad Education Trust'S. Pimpri Chinchwad College Of Engineering

12th, B.S. Memorial School, Aburoad

Public links

github: https://github.com/tiredhero21

leetcode: https://leetcode.com/hj0721