Help & Supportcareers@gravityer.com
AI Engineer with 1+ years in LLM-powered Agentic Systems & MLOps
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Machine Learning Engineer specialising in LLM-powered agentic systems, Retrieval-Augmented Generation (RAG) pipelines, and end-to-end MLOps, with 1.5+ years of production experience shipping AI applications to real users across AWS and GCP. Focused on building reliable, scalable AI infrastructure that directly improves user outcomes.
Guru Gobind Singh Indraprastha University (GGSIPU), ADGITM
Bachelor of Technology · Information Technology
August 1, 2021 – May 1, 2025
Shodh AI
Machine Learning Engineer
June 1, 2025 – Present
Jaipur, Rajasthan, India
Shodh AI
Machine Learning Intern
November 1, 2024 – June 1, 2025
New Delhi, Delhi, India
AI Game Master
January 1, 2025 – June 1, 2026
Architected a full-stack multi-agent RPG engine with a streaming Dungeon Master LLM agent and per-NPC dialogue agents, delivering real-time narrative token-by-token via Server-Sent Events (SSE) and parsing structured JSON world-state mutations each turn. Engineered a persistent NPC memory subsystem using ChromaDB vector embeddings and top-K semantic search (RAG), enabling NPCs to reference past interactions and evolve trust and disposition scores dynamically across sessions. Implemented autonomous world simulation via Celery Beat and Redis pub/sub: the LLM generates world events on a schedule, broadcasting updates live to all connected clients with zero player interaction required. Deployed a 6-service containerised stack (FastAPI, PostgreSQL, Redis, Celery, Next.js) via Docker Compose with Alembic migrations, async SQLAlchemy ORM, and an AI image generation pipeline (NVIDIA NIM / Flux.1-schnell) with content-hash caching.
Fake Medicine Detection System
January 1, 2024 – November 1, 2024
Built an end-to-end ML pipeline detecting counterfeit medicines from packaging images using OCR, custom Named Entity Recognition (NER), and similarity-based fraud detection, covering the full cycle from raw image ingestion to fraud verdict. Implemented EasyOCR-based text extraction and a custom SpaCy NER pipeline to identify drug name, manufacturer, and dosage, achieving ~85% entity extraction accuracy on held-out test samples. Optimised Computer Vision preprocessing and NLP inference to achieve low-latency predictions across 100+ medicine images, enabling near-real-time counterfeit screening at the point of dispensing. Developed a fraud detection module using Jaccard similarity against a trusted reference dataset, reducing false positives by ~25% over rule-based matching and improving overall detection reliability.
Cultural Fit Analysis
The candidate's project diversity, ranging from an AI Game Master to a Fake Medicine Detection System, showcases a broad interest in AI applications. Their experience at Shodh AI, moving from intern to ML Engineer, indicates growth and commitment. The skills listed align well with an AI Engineer role, demonstrating a strong cultural fit for a technically demanding and innovative environment.
Soft Skills & Operational Fit
The candidate demonstrates strong communication skills through detailed project and experience descriptions. Their involvement in multi-agent systems and distributed computing suggests good collaboration and operational fit for complex AI engineering roles. The mention of reducing operational incidents and improving system reliability indicates a proactive and problem-solving attitude.