AI Research Internship

About Lexsi Labs

Lexsi Labs is a frontier lab focused on building aligned, interpretable, and safe Superintelligence. Our work involves creating new methodologies for efficient alignment, interpretability strategies, and tabular foundational model research. We aim to create AI tools that empower researchers, engineers, and organizations while maintaining transparency and safety. Our team values curiosity, initiative, and collaboration.

About the Role

As a research intern at Lexsi Labs, you will work on large-scale industry problems and advance AI technologies in a fast-paced, innovative environment. This is a full-time internship (6 months, with potential for extension or full-time offer).

Key Responsibilities

You will collaborate closely with research and engineering teams on one of the following areas:

• Library Development: Architect and enhance open-source Python tooling for alignment, explainability, model alignment, uncertainty quantification, robustness, and machine unlearning.
• Explainability & Trust: Improve and discover new observations using XAI techniques (e.g., DLB, LRP, SHAP, Grad-CAM, Backtrace) across text, image, and tabular data to understand and present new model interpretability.
• Mechanistic Interpretability: Probe internal model representations and circuits using methods like activation patching and feature visualization to diagnose failure modes and emergent behaviors.
• Uncertainty & Risk: Develop, implement, and benchmark uncertainty estimation methods (e.g., Bayesian approaches, ensembles, test-time augmentation) and robustness metrics for foundation models.
• Tabular Foundational Models (Orion): Improve and launch new tabular foundational model architectures and contribute to the open-source library TabTune.
• Reinforcement Learning: Explore new ideas and algorithms around RL and our RL fine-tuning library.
• Research Contributions: Author and maintain experiment code, conduct systematic studies, and co-author whitepapers or conference submissions.

Requirements & Tech Stack

• 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 models like BERT, GPT, LLaMA, T5, MOE, Mamba.
• 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 is beneficial)

• Explainability: applied experience with XAI methods such as DLB, 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.
• LLM Alignment techniques: prompt crafting (few-shot, zero-shot, chain-of-thought), RLHF workflows, reward modeling, and human-in-the-loop fine-tuning.
• Tabular Foundational Models: experience with or improvements to models like Orion, TabPFN, TabICL.
• Post-training adaptation & fine-tuning: practical work with full-model fine-tuning, parameter-efficient methods (LoRA, adapters), instruction tuning, knowledge distillation, and domain-specialization.

Additional Experience (Nice-to-Have)

• Publications: contributions to top-tier AI/ML conferences (e.g., 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.
• 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.