Ruchit Shah

Software Engineer

Bengaluru, Karnataka, India4 yrs 10 mos experience

Highly StableAI Enabled

Key Highlights

Expert in Large Language Model Operations and Generative AI.
Designed impactful data pipelines for search relevance.
Proven track record in automating data quality processes.

Stackforce AI infers this person is a Backend-heavy Fullstack Engineer specializing in AI and data-driven solutions.

Contact

Skills

Core Skills

Large Language Model Operations (llmops)Generative AiPythonAmazon Web Services (aws)Computer Science

Other Skills

MongoDBWeb ScrapingMachine LearningPySparkApache AirflowUnit TestingSystems DesignObject Oriented DesignSoftware DevelopmentGitProblem SolvingAPI DevelopmentIdentifying IssuesBug TrackingAnalytical Skills

About

Working in the Search Science and AI org which is responsible to determine and improve the quality of search results across Amazon production (retail, prime, audible, etc) worldwide.

Experience

4 yrs 10 mos

Total Experience

3 yrs 8 mos

Average Tenure

1 yr 2 mos

Current Experience

Uber

Software Development Engineer 2

Apr 2025 – Present · 1 yr 2 mos · Bengaluru, Karnataka, India · Hybrid

Amazon

2 roles

Software Development Engineer 2, Search Relevance

Mar 2024 – Mar 2025 · 1 yr

◆ Large Language Model Inference Platform
Designed and developed an LLM model inference platform for labelling tasks, achieving a 500bps improvement
in F1 score over existing models.
Optimised architecture using prompt caching, resulting in a 10x reduction in model inference costs and
efficiency gains across the team.

Large Language Model Operations (LLMOps)Generative AI

Software Engineer, Search Relevance

Jul 2021 – Mar 2024 · 2 yrs 8 mos

◆ BigData Pipeline for Double Machine Learning Models
Main developer for designing and developing metric computation pipeline for search relevance impacting 50+ teams in the org.
Implemented automated data anomaly detection pipeline for monitoring data quality.
◆ Enhanced System with Event-Driven Architecture
Developed a comprehensive dashboard by integrating events into the existing system, enabling efficient monitoring of overall system status, including error logs and individual service failures.
Slashed weekly operational task time by around 8 hours through streamlined issue resolution using the developed dashboard.
Spearheaded the creation of an automated on-call issue log integrated with the operational dashboard, liberating the team from manual SIM management tasks, previously handled by the Program Manager
Conducted analysis to determine optimum sample size for metric computation, achieving a 50% reduction in computation costs without compromising accuracy.

PythonAmazon Web Services (AWS)

Dhirubhai ambani institute of information and communication technology

Research Intern

Jan 2021 – May 2021 · 4 mos · Gandhinagar, Gujarat, India

Analysed the robust way to automate the process of finding erroneous data points by finding outliers using the DBSCAN clustering algorithm. Assigned reliability index to each observer to ensure that the quality of the data in the analysis shouldn't be compromised.

MongoDBComputer Science

Amazon

Software Engineer Intern

May 2020 – Jun 2020 · 1 mo · Bengaluru, Karnataka

Automated data scrapping from news websites, Twitter, and Facebook using Beautiful Soup and Selenium. Utilised Elasticsearch for indexing and Word to Vector for accurate word cloud creation, enhancing trend analysis accuracy of most trending events

Web ScrapingComputer Science