DARSHAN Gowda M
Open to work2 years experienceAI Engineer
AI Engineer | GenAI & RAG Systems | LLM Applications | Cloud ML
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
32 skillsWork Experience
Assistant System Engineer — AI & Data
Tata Consultancy Services
- Architected a Medical Device Regulatory Submission Assistant using a RAG pipeline (Qdrant, Cohere, FastAPI) to automate FDA 510(k) predicate discovery, eliminating an estimated 80% of manual document search effort
- Developed a Vectorless PageIndex RAG system on Azure OpenAI GPT-4o with BM25Plus and LLM-driven hierarchical tree navigation, improving aviation AD document retrieval precision over baseline keyword search
- Engineered a 5-agent LangGraph Agentic Report Generation System with FAISS and BM25 hybrid r etrieval and self-correcting validation loops, achieving 2-3x faster throughput vs. sequential processing
- Released a cloud-native Predictive Analytics Dashboard on AWS SageMaker and S3, enabling HMW aggregate clearance prediction across 5 purification steps without wet-lab experiments — cutting experiment cycle time
- Standardized LLM prompt engineering practices across projects (temperature=0.0 for extraction, temperature=0.2 for generation), reducing hallucination incidents and improving output reliability in regulated environments
Projects
Medical Device Regulatory Submission Assistant
View Project- Constructed an end-to-end RAG pipeline for FDA 510(k) predicate discovery across a cor pus of cleared medical device PDFs; extracted Intended Use, Technical and Design Characteristics using Cohere command-r-plus at temperature=0.0
- Deployed a two-layer similarity system: dense vector cosine search for Intended Use matching and TF -IDF sentence-level matching for technical characteristics; auto-generated compliant 510(k) Summary Reports via LLM
Vectorless PageIndex RAG
View Project- Designed a retrieval-augmented pipeline without embedding vectors — using LLM-generated hierarchical document trees with entity enrichment (aircraft models, ATA codes, action keywords) and BM25Plus re - ranking for EASA AD documents
- Applied 6 systematic improvements over baseline RAG: entity-enriched tree nodes, iterative retrieval with sufficiency checks, query decomposition, normalized metadata filtering, BM25 post -filtering, and context budget management
Agentic Report Generation System
View Project- Orchestrated a 5-agent LangGraph pipeline (Planner, Retrieval, Writer, Validation, Assembly) with conditional routing that autonomously self-corrects report sections scoring below 7/10 on tone, purpose, and quality metrics
- Accelerated report generation by 2-3x through concurrent async section processing (asyncio and ThreadPoolExecutor) with hybrid retrieval combining 70% FAISS dense vectors and 30% BM25 sparse keyword search
DSP Predictive Analytics Dashboard
View Project- Produced an ML-powered Streamlit dashboard in the biopharmaceutical domain to predict High Molecular Weight (HMW) aggregate clearance across 5 purification steps using SageMaker -hosted models (Random Forest, Voting Ensemble; MSE 0.05-0.13)
- Integrated AWS S3 for centralized experimental data access and real-time SageMaker endpoint inference via boto3; embedded correlation heatmaps, clearance factor analytics, and scientific PDF export via FPDF and Kaleido
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
3rd Place Inter-Departmental Mini Project Exhibition
Secured 3rd place in Inter-Departmental Mini Project Exhibition — outperforming 25 competing teams
5th Place DevHacks 1.0 National Level Hackathon
Ranked 5th in DevHacks 1.0 National Level Hackathon — competing against 150+ participants across India
About Details
Professional Bio
AI Engineer at Tata Consultancy Services with 2 years of experience building production GenAI systems, RAG pipelines, and agentic AI workflows. Shipped 4 end-to-end AI solutions integrating Azure OpenAI, AWS SageMaker, and LangGraph for enterprise clients.
B.E. in Electronics and Communication Engineering
Don Bosco Institute of Technology (DBIT), Bengaluru (2020 - 2024)