Piyush Chandra
PROFESSIONAL SUMMARY
AI Research Engineer with nearly two years of experience across Python development, reinforcement learning, and machine-learning pipelines in research and industry settings. Specializes in reinforcement learning for LLM post-training: RL environment design, Reinforcement Learning with Verifiable Rewards (RLVR), Reinforcement Learning from Human Feedback (RLHF), reward modeling, policy optimization, and programmatic verifier engineering. Builds rubric-based evaluation frameworks and post-training data workflows spanning Supervised Fine-Tuning (SFT), reward modeling, GRPO, GTPO, and LoRA, alongside production-grade Agentic AI architectures that drive reliable, autonomous task execution.
WORK EXPERIENCE
- Drive end-to-end, Python-based reinforcement-learning and data-driven post-training pipelines that capture chain-of-thought, optimize model behavior, and improve task-based accuracy.
- Design and build simulated evaluation environments for Agentic AI systems and conversational AI agents, spanning complex multi-turn reasoning, code generation, mathematics, and agentic tool-use.
- Engineer programmatic verifiers and rubric-based evaluation frameworks that produce reliable, scalable reward signals for post-training.
- Author high-difficulty Python tasks, ground-truth solutions, and rubric-based evaluations used in post-training and model assessment.
- Build internal tooling and dashboards (Python, plus React + TypeScript) supporting model training, evaluation workflows, and operational efficiency.
- Led a small project team on a Government of India initiative analysing the domestic Electric Vehicle (EV) market, owning scope and milestones and running end-to-end market-segmentation analysis to identify levers for accelerating consumer adoption.
- Built K-Means clustering and decision-tree models on multi-source datasets (sales, demographic, geographic, charging infrastructure) to profile high-propensity consumer cohorts across Indian states.
- Mapped supply-side chokepoints across battery sourcing, charging infrastructure, and OEM distribution; engineered the full Python data pipeline (pandas, NumPy, scikit-learn) and presented findings via dashboards and a written report.
TECHNICAL SKILLS
Reinforcement Learning: RL Environment Design, Reinforcement Learning with Verifiable Rewards (RLVR), RL from Human Feedback (RLHF), Reward Modeling, Policy Optimization, Verifier Engineering, Evaluation Design
LLM Post-Training: Supervised Fine-Tuning (SFT), Reward Modeling, GRPO, GTPO, LoRA Fine-Tuning, Chain-of-Thought Design, Rubric-Based Evaluation
Agentic AI: Agentic AI Architectures, Agent Tools, Conversational AI Agents, Multi-Turn Reasoning, Simulated Evaluation Environments, Agentic Tool-Use Evaluation
AI / Machine Learning: Natural Language Processing, Prompt Engineering, Multimodal Reasoning, Classification, Clustering, Predictive Modeling
Languages: Python, C++, TypeScript, SQL
Frameworks & Tools: PyTorch, HuggingFace, Weights & Biases (W&B), pandas, NumPy, scikit-learn, React, Next.js, Jupyter, pytest, Docker, Git
Cloud & Infrastructure: AWS, GCP, Native API Integration
Data: Exploratory Data Analysis (EDA), Data Curation, Data Cleaning, Feature Engineering, Data Visualization
EDUCATION
CERTIFICATIONS
- AIF | BlackRock: Data Science