Aditya Kanamadi
Open to work1 years experienceApplied AI Engineer
Applied AI Engineer focused on building scalable AI systems with LLMs, RAG, and autonomous agent architectures.
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
24 skillsWork Experience
AI Engineer
Perceptyx AI
- AI search engine that answers user queries using real-time web search with citations.
- Built a multi-layer memory combining working, episodic, semantic and procedural memory to improve context retention and response quality across sessions.
- Implemented intelligent query routing, search aggregation, and reranking; reduced AI search latency ~40% via parallel retrieval, async Qdrant queries, and Redis semantic caching.
- Built scalable background workflows with monitoring and RLHF-based self-learning loops for continuous improvement.
Projects
Time Series-Forecasting-Platform
View Project- Built a production ready forecasting API serving dynamic 8-week predictions with <1s latency across multiple regions.
- Developed an automated ML pipeline with ARIMA, Prophet, XGBoost, and LSTM model selection using sMAPE scoring; optimized deployments with Docker layer caching and uv dependency management.
Resume Ranker
View Project- Built an offline, CPU-efficient AI Resume Ranker that semantically matches 100k+ candidate profiles to job descriptions using Sentence Transformers (BAAI/bge-small-en-v1.5) and FAISS - no external LLM APIs required.
- Engineered a hybrid multi-factor scoring pipeline using Python, Polars, FAISS, RapidFuzz, and Pydantic, integrating semantic similarity, skill matching, experience signals, and honeypot detection to generate explainable candidate ranking.
- Optimized retrieval with precomputed embeddings, vectorized scoring, and deterministic rule-based explanations, achieving Top-100 ranking from 100k candidates in ~2 seconds on CPU.
Open-Source
View Project- Built a secure RAG system with multi-layer defence including input sanitization, prompt injection detection, output filtering, and role-based context separation.
- Developed an intelligent cloud anomaly detection system using hybrid ML and LLM reasoning, reducing false positives and accelerating incident response.
- Built AI memory module for agentic systems, improving long-term context retention across multi-turn interactions.
- Worked on ML algorithms, data preprocessing, feature engineering, model training, evaluation, optimization, cross-validation, Prompt Engineering, LLMs fine-tuning, LLM Evaluations.
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 Search Latency Reduction
Reduced AI search latency ~40% via parallel retrieval, async Qdrant queries, and Redis semantic caching.
Resume Ranker Optimization
Achieved Top-100 ranking from 100k candidates in ~2 seconds on CPU.
About Details
Professional Bio
Applied AI Engineer focused on building scalable AI systems with LLMs, RAG, and autonomous agent architectures. Skilled in developing end-to-end ML pipelines, vector search, model evaluation, and production deployment using Docker, FastAPI, LangChain, LangGraph, and modern AI infrastructure.
Bachelor of Engineering in Electronics & Communication
Visvesvaraya Technological University (2021 - 2025)