AI Research Scientist (Internship)

Alpha Z; United States; Remote; USD 85,000 - 140,000; Full time

Job summary

Alpha Z is seeking a researcher or research engineer to explore how large language models can enhance optimization and operations research tasks. You will investigate LLM-based methods for mathematical modeling, problem formulation, algorithm design, solver selection, and decision-support workflows.

You'll develop and test workflows involving coding with LLMs in the loop, study how LLMs can generate, debug, verify, and improve optimization models and solver code, and design evaluation methods

Qualifications

• Experience in optimization, LLMs, AI agents, or algorithms.
• Ability to translate business problems into mathematical models.
• Strong research ability and technical depth in related fields.

Responsibilities

• Conduct research on how LLMs support optimization and OR tasks.
• Explore LLM-based methods for modeling, formulation, and solver selection.
• Develop workflows involving coding with LLMs in the loop.
• Study generation, debugging, verification, and improvement of models and code.
• Design benchmarks for LLM-generated formulations and solutions.
• Implement research prototypes and computational experiments.
• Analyze failures and improve model reliability and usefulness.

Skills

Optimization

LLMs

AI agents

Algorithms

Machine learning

Communication

Education

Bachelor's/Master's/PhD students welcome

Tools

Gurobi

CPLEX

SCIP

OR-Tools

Job description

What you\'ll do.

• Conduct research on how large language models can support optimization and operations research tasks.
• Explore LLM-based methods for mathematical modeling, problem formulation, algorithm design, solver selection, and decision-support workflows.
• Develop and test workflows involving coding with LLMs in the loop.
• Study how LLMs can generate, debug, verify, and improve optimization models and solver code.
• Design evaluation methods and benchmarks for LLM-generated optimization formulations, code, and solutions.
• Implement research prototypes and computational experiments.
• Analyze failure cases and improve model reliability, correctness, and usefulness.

What we look for.

• Candidates pursuing a PhD, Master's degree, or Bachelor's degree in relevant fields are welcomed.
• Demonstrated research ability, strong technical depth, and experience in optimization, LLMs, AI agents, algorithms, or machine learning are highly valued.
• Ability to work independently in a fast-paced startup environment with evolving priorities.
• Excellent communication skills for discussing technical concepts with cross-functional teammates.

Technical expertise.

• Optimization & Modeling.
• Experience with LP, MIP, NLP, or constraint programming.
• Ability to translate business problems into mathematical models (variables, objectives, constraints).
• Familiarity with solvers like Gurobi, CPLEX, SCIP, or OR-Tools.
• Understanding of solver behavior, computational bottlenecks, and model debugging.
• Experience with practical problems such as routing, scheduling, or resource allocation.
• Engineering & AI.
• Expertise in code structure, testing, logging, and building reproducible experiment pipelines.
• Ability to integrate AI components with external tools, APIs, and enterprise systems.
• Strong judgment on system performance, scalability, and failure handling.Knowledge of LLM workflows (prompting, retrieval, agents), machine learning evaluation, and structured code generation.