Siddhant Gahoi
Open to work2 years experienceSoftware Engineer - AI/ML
Software Engineer - AI/ML
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
26 skillsGitHub Activity Evidence
GitHub Footprint Not Connected
Recruiters value verified code contributions. Linking a GitHub account displays live heatmaps, active contribution metrics, repository languages, and push activity tags.
Work Experience
Software Engineer - AI/ML
Sanjay Gupta and Associates
- Developed an AI-powered legal research assistant using LLMs, LangChain, and RAG, reducing legal research time by 70% and increasing document retrieval accuracy by 35%.
- Built a semantic search engine using Qdrant and Sentence Transformers to index over 2GB+ legal documents, achieving an average query response time of under 2 seconds.
- Automated contract summarization and clause extraction, reducing manual document review time by 60% and processing over 1,500 contracts per month.
AI Engineer
Escape Enterprises
- Built an AI-powered wellness chatbot using LangChain, delivering 90% accurate personalized recommendations.
- Developed a multimodal emotion-detection system (text + image), boosting user engagement and personalization.
- Integrated optimized REST APIs, improving data retrieval speed by 25%.
- Built dynamic, responsive UI components in Flutter, reducing app load time by 10%.
- Contributed to full-stack app architecture using API orchestration and scalable front-end modules
Projects
Vision Chatbot (Aaron)
- Engineered a Multimodal Agentic Workflow using LangGraph and Llama 3.2 , achieving a 95%+ intent classification accuracy by implementing conditional edges to route queries between conversational responses, YOLOv8 object detection, and DuckDuckGo web search.
- Developed a High-Performance Vision Pipeline integrating YOLOv8 as a custom tool; optimized inference by utilizing local file-system paths for image processing, resulting in sub-second object detection results within a stateful chat environment.
- Architected a Full-Stack AI Platform with a FastAPI backend and React frontend, implementing InMemorySave r for persistent thread-based memory and automated file cleanup tasks to maintain server stability and 0% disk bloat during high-frequency usage.
AI Anime Recommender System
- Engineered a robust RAG pipeline utilizing ChromaDB for vector storage and Groq/Hugging Face APIs for high-speed inference, enabling real-time personalized recommendations..
- Developed a decoupled "Recommender Class" and custom prompt templates to ensure high maintainability and scalable logic between data loading and model output.
- Scaled the application from a Streamlit frontend to a production-ready GCP VM using Docker and Kubernetes (K8s) for automated container orchestration.
- Integrated Grafana Cloud for real-time monitoring of model performance and system health, ensuring 99.9% uptime and proactive error handling via custom exception logging..
Flipkart Product Recommender System
- Architected a Full-Stack RAG Applicatio n using Python and Flask, developing custom ingestion modules that reduced context retrieval latency by 35% and improved response relevancy through optimized chunking strategies and vector embeddings.
- Developed an evaluation framework to measure retrieval accuracy, precision, and response latency, enabling iterative optimization of chunking strategies and embedding models.
- Engineered a Scalable Microservices Architecture by containerizing services with Docker and orchestrating with Kubernetes (Minikube) , achieving a 40% improvement in deployment frequency and ensuring 99.9% uptime through automated health checks.
Cache Simulator
- Developed a configurable cache simulator supporting multiple cache organizations and replacement algorithms.
- Implemented LRU and FIFO eviction policies using hash maps and linked lists for efficient cache management.
- Simulated thousands of memory accesses while tracking cache hits, misses, evictions, and write-back events.
- Designed reusable object-oriented modules for cache sets, cache lines, and memory hierarchy simulation.
- Validated correctness using custom test cases and benchmark memory traces.
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
AI-powered legal research assistant
Developed an AI-powered legal research assistant using LLMs, LangChain, and RAG, reducing legal research time by 70% and increasing document retrieval accuracy by 35%.
Semantic search engine
Built a semantic search engine using Qdrant and Sentence Transformers to index over 2GB+ legal documents, achieving an average query response time of under 2 seconds.
About Details
Professional Bio
Software Engineer specializing in AI/ML with expertise in LLMs, RAG, and full-stack development. Experienced in building scalable AI platforms, semantic search engines, and automated workflows using LangChain, FastAPI, and React.
Master of Science in Computer Science
Arizona State University (2022 - 2024)
Bachelor of Technology in Computer Science
Vellore Institute of Technology (2018 - 2022)