Job Description

AI Research Intern - AryaXAI AI Alignment Labs
Commitment: Full-time internship (6 months; potential extension or full-time offer)
Start Date: Rolling
About AryaXAI AI Alignment Labs
AryaXAI AI Alignment Labs, based out of Mumbai, India and Paris, France, is the alignment and explainability division of , part of Aurionpro Solutions. We work on AI interpretability and trustworthiness for mission-critical sectors. Our open-source initiatives include the xai_evals benchmarking suite and the DLBacktrace explainability framework, both designed to make AI more transparent, reliable, and aligned with human values.
What You'll Do
Collaborate closely with our research and engineering teams on one of the areas:

• Library Development: Architect and enhance open-source Python tooling for alignment, explainability, uncertainty quantification, robustness, and machine unlearning.
• Model Benchmarking: Conduct rigorous evaluations of LLMs and deep networks under domain shifts, adversarial conditions, and regulatory constraints.
• Explainability & Trust: Design and implement XAI techniques (LRP, SHAP, Grad-CAM, Backtrace) across text, image, and tabular modalities.
• Mechanistic Interpretability: Probe internal model representations and circuits--using activation patching, feature visualization, and related methods--to diagnose failure modes and emergent behaviors.
• Uncertainty & Risk: Develop, implement, and benchmark uncertainty estimation methods (Bayesian approaches, ensembles, test-time augmentation) alongside robustness metrics for foundation models.
• Research Contributions: Author and maintain experiment code, run systematic studies, and co-author whitepapers or conference submissions.

General Required Qualifications

• Strong Python expertise: writing clean, modular, and testable code.
• Theoretical foundations: deep understanding of machine learning and deep learning principles with hands-on experience with PyTorch.
• Transformer architectures & fundamentals: comprehensive knowledge of attention mechanisms, positional encodings, tokenization and training objectives in BERT, GPT, LLaMA, T5, MOE, Mamba, etc.
• Version control & CI/CD: Git workflows, packaging, documentation, and collaborative development practices.
• Collaborative mindset: excellent communication, peer code reviews, and agile teamwork.

Preferred Domain Expertise (Any one of these is good) :

• Explainability: applied experience with XAI methods such as SHAP, LIME, IG, LRP, DL-Bactrace or Grad-CAM.
• Mechanistic interpretability: familiarity with circuit analysis, activation patching, and feature visualization for neural network introspection.
• Uncertainty estimation: hands-on with Bayesian techniques, ensembles, or test-time augmentation.
• Quantization & pruning: applying model compression to optimize size, latency, and memory footprint.
• LLM Alignment techniques: crafting and evaluating few-shot, zero-shot, and chain-of-thought prompts; experience with RLHF workflows, reward modeling, and human-in-the-loop fine-tuning.
• Post-training adaptation & fine-tuning: practical work with full-model fine-tuning and parameter-efficient methods (LoRA, adapters), instruction tuning, knowledge distillation, and domain-specialization.

Additional Experience (Nice-to-Have)

• Publications: contributions to CVPR, ICLR, ICML, KDD, WWW, WACV, NeurIPS, ACL, NAACL, EMNLP, IJCAI or equivalent research experience.
• Open-source contributions: prior work on AI/ML libraries or tooling.
• Domain exposure: risk-sensitive applications in finance, healthcare, or similar fields.
• Performance optimization: familiarity with large-scale training infrastructures.

What We Offer

• Real-world impact: address high-stakes AI challenges in regulated industries.
• Compute resources: access to GPUs, cloud credits, and proprietary models.
• Competitive stipend: with potential for full-time conversion.
• Authorship opportunities: co-authorship on papers, technical reports, and conference submissions.