Jaya Soorya V
Open to work0 years experienceMachine Learning Engineer
Machine Learning Engineer specializing in LLM/SLM fine-tuning and RAG pipelines.
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
37 skillsWork Experience
Machine Learning Engineer - I
Manthhan Software Pvt. Ltd.
- Fine-tuning SLMs and BERT-family models using LoRA, QLoRA, and PEFT for domain-specific document classification and structured extraction; applied 4-bit NF4 quantisation via bitsandbytes, reducing GPU memory footprint significantly with minimal accuracy drop.
- Owning end-to-end development of a RAG-based automated compliance checking system; built retrieval pipeline (chunking, AWS Bedrock embeddings, vector search), LLM reasoning layer, and deviation flagging module achieving 94% compliance detection accuracy across vendor bid documents.
- Architecting document workflows with hash-based fingerprinting for deduplication and multi-stage parsing; orchestrated via Prefect with MongoDB, AWS S3/MinIO storage.
- Managing CI/CD-aligned ML lifecycle on AWS SageMaker with MLflow experiment tracking, Git versioning, and Docker-containerised deployments; applied quantisation and model compression to reduce inference latency in production.
Projects
HawkAi – Real-Time Intruder Detection
View Project- Two-stage classification pipeline (92.5% accuracy, 22ms/frame on edge device) with RFID verification. Novel approach underpatent filing.
EV Energy Optimizer
View Project- Predicted EV energy consumption (MAE: 0.0238) from terrain and weather features; compared GRU vs LSTM vs linear baselines. 2nd place, Raptee × Zoho × VIT Hackathon.
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
Hackmatrix 2025 2nd Place
Hackmatrix 2025 – 2nd Place (IIT Patna, 900+ teams)
VEL IDEA FORGE 2K25 3rd Place
VEL IDEA FORGE 2K25 – 3rd Place
About Details
Professional Bio
Machine Learning Engineer with production experience in LLM/SLM fine-tuning (LoRA, QLoRA, PEFT) and RAG pipeline development on AWS. Built and scaled a document compliance pipeline achieving 94% accuracy across 100,000+ pages of enterprise documents.
B.Tech – Computer Science & Engineering (AI & ML) in Computer Science & Engineering (AI & ML)
Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai (2022 - 2026)