Rohan Jain

Agentic AI Engineer

Artificial Intelligence and Machine Learning
2roles
44skills
2education

About

Electronics and Instrumentation Engineering student focused on agentic AI, reinforcement learning, LLM systems, RAG, and autonomous AI applications.

Experience

Agentic AI Engineer

Quarq

Apr 2026 – May 2026

Designed and implemented a multi-agent orchestration platform executing multi-step tool workflows via a ReAct loop architecture, enabling autonomous task decomposition and iterative self-correction. Implemented prompt engineering patterns including Chain-of-Thought reasoning, progressive skill-disclosure routing, and a Temporal Truth Protocol for resolving memory contradictions across agent turns.

AI/ML Engineer Intern

Nutrail Cognitive Analytics

Sep 2025 – Mar 2026

Engineered a Memory + RAG backend using LlamaIndex vector embeddings for long-term context persistence across 10+ turns. Designed a multi-agent pipeline for sentiment, clinical assessment, safety guardrails, and report generation deployed in production for mental health evaluation. Built a production voice AI system using Groq ASR, Gemini LLM, and TTS with stateful conversational loops and real-time audio processing across 20+ languages.

Education

Jadavpur University

B.E., Electronics and Instrumentation Engineering

Sep 2023 – May 2027

GPA: 8.4

M.C. Kejriwal Vidyapeeth

Class XII – ISC and Class X – ICSE

Class XII: 97.5% (School Topper); Class X: 97.4%

Skills

PythonC/C++JavaJavaScriptTypeScriptMATLABPyTorchTRLGRPOPPODQNUnslothScikit-learnNumPyPandasLangChainLangGraphLlamaIndexReActChain-of-ThoughtFine-tuningQLoRAKelly CriterionReward ShapingCurriculum LearningEnsemble ForecastingChromaDBPineconeNeo4jFAISSPostgreSQLRedisFastAPIDockerGCPGradioStreamlitSupabaseHuggingFace HubLinear AlgebraProbability and StatisticsDBMSData Structures and AlgorithmsComputer Networks

Projects

ALICE – Adversarial Co-Evolutionary RL Training Environment

Built an adversarial co-evolutionary reinforcement learning environment using PyTorch, TRL, GRPO, Unsloth, Qwen2.5, and Gradio. Implemented the OHRV cycle in which an Oracle generates hard scenarios, a Hunter attempts them, Repair corrects failed trajectories, and Verify validates them. Added auto-scaling environment difficulty, custom reward shaping, GRPO training, and a real-time Gradio dashboard for reward curves, win-rate evolution, and difficulty progression. Selected among the top teams in the Meta PyTorch OpenEnv Hackathon Grand Finale out of 52,000+ developers.

ORACLE – Autonomous AI Trading Agent

Built an autonomous prediction market agent for the AI Forecasting Hackathon 2026 at the University of Chicago using ensemble forecasting, news sentiment, market signals, Kelly Criterion position sizing, and the Kalshi API. Engineered real-time monitoring to calculate gaps between estimated edge and implied probability and execute trades above a calibrated confidence threshold.

Hybrid RAG Travel Planner

Built a FastAPI backend combining Neo4j knowledge graph traversal with ChromaDB and Pinecone vector search, achieving a reported 92% improvement in personalization. Orchestrated multi-step LLM reasoning with LangGraph to resolve complex multi-hop queries at sub-second latency.