Help & Supportcareers@gravityer.com
AI Engineer with less than a year in LLMs & Multimodal AI
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Highly motivated and results-oriented AI/ML and Generative AI Engineer with 11 months of experience in designing and developing end-to-end multimodal AI pipelines. Proficient in LLMs, RAG, fine-tuning, and workflow orchestration, with a strong background in Python, PyTorch, and TensorFlow. Adept at optimizing backend services, building agentic systems, and implementing MLOps-driven solutions to enhance system scalability and reliability.
Indian Institute of Information Technology, Design and Manufacturing, Kurnool
B.Tech · Artificial Intelligence and Data Science
August 1, 2022 – June 30, 2026
Timepilot
ML & GenAI Engineer Intern
February 1, 2026 – Present
India
IITM Pravartak Foundation
AI Project Intern
April 1, 2025 – July 31, 2025
Chennai, Tamil Nadu, India
NIT Warangal
Research Summer Intern
May 1, 2024 – June 30, 2024
India
Triplet-Enhanced RAG for Cross-Lingual QA System
January 1, 2024 – June 30, 2026
Engineered a triplet-enhanced cross-lingual RAG pipeline for multilingual question answering across Telugu, Bengali, Arabic, and Korean using the XOR-TyDi QA benchmark. Implemented a hybrid retrieval architecture combining BM25 sparse search, CrossEncoder reranking, and REBEL-based triplet extraction with query-aware semantic ranking for structured NLP context generation. Conducted ablation studies across four RAG architectures - Sparse, Reranked, Triplet, and Triplet-Enhanced, achieving up to +12.61 F1 improvement over multilingual QA baselines.
View ProjectAI Persona Agent - Voice Agent & RAG Chat with Live Calendar Booking
January 1, 2024 – June 30, 2026
Developed a voice agent that answers questions about the candidate's background, projects, and experience using Vapi, Deepgram STT, and GPT-4o, achieving ~1.15s first-response latency. Built a two-source RAG pipeline over resume sections and GitHub READMEs using ChromaDB and Groq LLaMA-3.3-70B, validated through an LLMops evaluation framework achieving 0% hallucination rate on a 15-question golden eval set. Deployed end-to-end on HuggingFace Spaces with a Streamlit chat interface and Cal.com integration for real-time slot booking and automated confirmation emails, achieving 8/8 booking completions with no human in the loop.
View ProjectMALLM: Malware Analysis with Large Language Models
January 1, 2024 – June 30, 2026
Architected a two-stage malware analysis pipeline for systematic detection and family-wise classification using behavioral analysis of CAPEv2 sandbox execution reports. Fine-tuned open-source LLMs using LoRA-based PEFT and combined LLM-generated behavioral embeddings with ML classifiers including XGBoost and Random Forest for semantic malware analysis. Achieved 97.85% malware detection accuracy and 97.13% family classification accuracy, with findings published at ICISCN 2026.
View ProjectCultural Fit Analysis
The candidate's academic background in AI and Data Science, coupled with multiple internships and research publications, aligns well with a culture that values continuous learning, innovation, and technical excellence. Their involvement in diverse projects, including those with real-world applications (e.g., SEC filings processing, calendar booking), suggests a practical and results-oriented mindset. The achievements, such as gold medals and GATE ranking, indicate a high-achieving individual who can thrive in a challenging and competitive environment.
Soft Skills & Operational Fit
The candidate demonstrates strong initiative and a proactive approach to learning and applying advanced AI/ML concepts. Their project descriptions highlight a methodical approach to problem-solving, including evaluation frameworks and ablation studies. The ability to work on diverse projects, from voice agents to malware analysis, suggests adaptability and a strong work ethic. Experience with Git-based collaboration and MLOps practices indicates readiness for team environments and production-grade systems.