AI Research Internship

About Lexsi Labs

Lexsi Labs is a leading frontier lab focused on building aligned, interpretable, and safe Superintelligence. The work involves creating new methodologies for efficient alignment, interpretability lead-strategies, and tabular foundational model research. The mission is to create AI tools that empower researchers, engineers, and organizations to unlock AI's full potential while maintaining transparency and safety. The team thrives on a shared passion for cutting-edge innovation, collaboration, and a relentless drive for excellence. Lexsi.ai operates with a flat organizational structure that values curiosity, initiative, and exceptional performance.

About the Role

As a research intern at Lexsi.ai, you will be uniquely positioned to work on very large-scale industry problems and push forward the frontiers of AI technologies. You will become part of an atmosphere where startup culture meets research innovation, with key outcomes of speed and reliability. This is a full-time internship with a commitment of 6 months, with potential for extension or a full-time offer.

Key Responsibilities

Work on one of the following areas, collaborating closely with research and engineering teams:

• Library Development: Architect and enhance open-source Python tooling for alignment, explainability, model alignment, uncertainty quantification, robustness, and machine unlearning.
• Explainability & Trust: Improve and find new observations using SOTA XAI techniques (e.g., DLB, LRP, SHAP, Grad-CAM, Backtrace) across text, image, and tabular modalities 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) alongside robustness metrics for foundation models.
• Tabular Foundational Models (Orion): Work with the Tabular Foundational Model team to improve and launch new tabular foundational model architectures and work on the open-source library TabTune.
• Reinforcement Learning: Explore new ideas and algorithms around RL and the new RL fine-tuning library.
• Research Contributions: Author and maintain experiment code, run 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 of these 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 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.
• Tabular Foundational Models: experience with or improvement of TFMs like Orion, TabPFN, TabICL.
• Post-training adaptation & fine-tuning: practical work with full-model fine-tuning and parameter-efficient methods (e.g., 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.