Chinmay Malkar
Open to work3 years experienceAI Engineer
AI Engineer | Data Scientist
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
25 skillsWork Experience
Data Scientist I
Bristol Myers Squibb
- Architected a semantic router for the RAG system, routing 40% of queries (FAQ and greetings) away from the full pipeline and reducing response latency from 2s to 300ms by bypassing vector search and LLM inference
- Built and deployed a semantic data matching system using Sentence-BERT embeddings, achieving 98.5% precision and reducing manual reconciliation effort by 15+ hours/week
- Developed a decision-intelligence engine on Aera using historical planning patterns, automating 40% of routine supply chain decisions with zero manual intervention
- Automated end-to-end data delivery to AWS S3 using SQL pipelines, reducing manual effort by ~5 hours/week and enabling direct data ingestion for 5+ production ML models
- Implemented KPI dashboards and evaluation frameworks to track decision accuracy and user adoption across 2 planning teams, enabling continuous optimization of automated workflows
Associate Data Scientist (AI Engineering)
JIO Platforms Ltd
- Designed and deployed a RAG-based chatbot (vector search + LLMs) using Milvus, improving response accuracy by 40%
- Fine-tuned Mistral LLM (LoRA) to improve adversarial prompt generation success rate from 30% -> 85%
- Built a Prompt Injection Test Suite for evaluating LLM applications under adversarial attacks, achieving 92% risk detection accuracy
- Engineered a PII detection framework for LLM-generated outputs, reducing sensitive data leakage risk with 89% detection accuracy
- Developed an LLM-powered recommendation engine for generating context-aware follow-up queries, increasing user engagement by 35%
- Designed a document intelligence pipeline (YOLO) to extract structured data from PDFs, improving extraction accuracy by 30%
- Scaled and optimized a big data pipeline (PySpark/SQL) processing 6+ TB of data daily
Projects
Exploratory Data Analysis Agent
- Created a multi-agent EDA system using LangGraph and LLMs to autonomously perform data profiling, statistical analysis, and insight generation
- Engineered agent-based workflows for feature analysis, correlation detection, and anomaly identification, improving analysis efficiency by 40%
AutoDocGen Agent
- Orchestrated a LangGraph-based multi-agent documentation generator that analyzes GitHub repositories and local codebases to produce structured Markdown documentation across 8 sections
- Architected a scalable 4-agent orchestration pipeline with adaptive chunking for repositories exceeding 50K LOC and parallel LLM summarization, reducing documentation generation time by ~50%
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Achievements Not Earned
Special rewards, developer badges, system recognition certificates, and conceptual milestones will display here.
About Details
Professional Bio
AI Engineer with 2.9+ years of experience building production-grade LLM systems, RAG pipelines, and agentic AI workflows. Delivered measurable business impact through semantic routing, supply chain automation, and LLM security frameworks at Bristol Myers Squibb and Jio Platforms.
B.E. Computer Engineering in Computer Engineering
Pillai College Of Engineering (2019 - 2023)