Help & Supportcareers@gravityer.com
AI Engineer with less than a year in LLM Engineering with 0.0 Years in RAG pipelines & Multi-agent O
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Computer Science undergraduate specializing in applied LLM engineering, RAG pipelines, multi-agent orchestration, and AI evaluation systems. I have built production-oriented AI applications using LangChain, Qdrant, FastAPI, and Ollama with a focus on reliability, hallucination detection, and developer-friendly design.
Manipal University Jaipur
B.Tech · Computer Science and Engineering
August 1, 2023 – June 30, 2027
openAudit-reasoner-V2
January 1, 2026 – Present
Architected a multi-agent LLM orchestration platform instantiating four specialized reasoning agents (Fast, Careful, Creative, Critical) from a single local model, enabling parallel perspective generation on any user query. Built an agent evaluation layer that scores outputs across all four reasoning perspectives, flags disagreements between agents as uncertainty signals, and produces structured evaluation logs enabling fully auditable, explainable agent decisions. Engineered transparent chain-of-thought visualization exposing step-by-step reasoning paths for each agent side-by-side, transforming opaque LLM outputs into inspectable decision traces.
View ProjectDevSearch-AI
January 1, 2026 – Present
Engineered a local-first knowledge assistant with 6 authenticated user roles, role-based document access, admin uploads, and audit logging for internal document retrieval. Improved retrieval relevance by combining Qdrant vector search with lexical score boosting and role-aware filtering for policy and knowledge-base queries. Exposed backend APIs for authentication, chat, audit logs, and document ingestion, and containerized the stack with Docker Compose for reproducible local deployment.
View ProjectEmotion Classification Chatbot
January 1, 2026 – Present
Built a 5-class emotion classification chatbot benchmarking 3 models (Naive Bayes + BoW, Logistic Regression + TF-IDF, Linear SVM +TF-IDF) with unigram and bigram features. Added custom preprocessing (negation, contractions, intensifiers, stemming) and produced full evaluation artifacts: confusion matrices, macro F1, MCC, FPR/FNR practicing structured evaluation methodology.
View ProjectCode for Bharat Season 2 - Finalist among 14,000+ teams
Code for Bharat
June 1, 2026 – Present
Deep Learning Specialization
DeepLearning.AI
June 1, 2026 – Present
CodeChef - Solved 150+ DSA problems
CodeChef
June 1, 2026 – Present
Red Hat System Administration I and II
Red Hat
June 1, 2026 – Present
PwC Launchpad Program 2026 - Selected for Data Analytics Track
PwC
June 1, 2026 – Present
Retrieval Augmented Generation (RAG)
DeepLearning.AI
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project portfolio demonstrates a strong alignment with the target role of an AI Engineer, showcasing diverse applications of LLMs, RAG, and multi-agent systems. The certifications from DeepLearning.AI and participation in programs like PwC Launchpad and Code for Bharat indicate a proactive learning attitude and a drive for continuous improvement, which are positive indicators for cultural fit. The breadth of technical skills, from core programming to system administration, suggests adaptability and a willingness to tackle various challenges.
Soft Skills & Operational Fit
The candidate's project descriptions highlight an ability to architect complex systems (multi-agent LLM orchestration) and focus on auditable, explainable AI decisions, suggesting a methodical and quality-oriented approach. The emphasis on 'developer friendly design' and 'reproducible local deployment' indicates an understanding of operational best practices. However, without direct interview data or psychometric test results, specific soft skills like teamwork, leadership, or stress handling cannot be definitively assessed.