Engineering Expert

This is a fully remote position, open to applicants in India.

📋 Description

• Design, develop, and validate intricate engineering simulation challenges for the training and assessment of advanced AI models and coding agents.

• Create realistic, multi-constraint problems within the domains of Electrical, Mechanical, and Aerospace Engineering.

• Establish measurable objectives, validated reference solutions, and automated grading systems that can be objectively verified.

• Construct, configure, execute, and validate simulation-based problem environments utilizing open-source engineering tools.

• Develop Python scripts, custom test benches, and utilities to automate simulations and verify outcomes.

• Ensure that simulation outputs meet requirements for physical plausibility, dimensional consistency, boundary conditions, convergence criteria, and domain-specific constraints.

• Diagnose simulation failures, numerical instabilities, dependency issues, and computational errors.

• Assess LLMs and coding agents through repeated engineering problem-solving trials.

• Analyze execution trajectories, tool interactions, simulator feedback, and intermediate outputs to pinpoint failures in reasoning and tool usage.

• Adjust task difficulty and refine benchmarks based on empirical model performance and evaluation findings.

• Collaborate with AI researchers, technical leaders, and subject-matter experts to incorporate validated benchmarks into AI evaluation workflows.

⛳️ Requirements

• A Master's degree or PhD in Electrical Engineering, Mechanical Engineering, Aerospace Engineering, or a closely related technical field.

• A minimum of 10 years of hands-on engineering design experience.

• Proficient in Python programming and scripting.

• Practical experience with at least one relevant open-source engineering simulation or design tool, such as ngspice, PySpice, OpenFOAM, FEniCSx, CalculiX, python-control, OpenModelica, CadQuery, build123d, Cantera, or Gmsh.

• Experience in developing, executing, debugging, and validating simulation-based engineering workflows.

• Familiarity with contemporary LLMs, AI coding agents, and AI evaluation techniques.

• Ability to analyze model execution logs and detect failures in reasoning, planning, and tool utilization.

• Strong comprehension of physical constraints, units, boundary conditions, numerical convergence, and engineering validation.

• Excellent analytical, problem-solving, and technical documentation abilities.

• Capability to work independently and produce technically accurate results within set deadlines.

• Availability for approximately 40 hours per week.

• At least 4 hours of daily overlap with US Pacific Time.

• Availability for weekend on-call duties.

• Access to a personal desktop or laptop.

• Reliable, high-speed internet connection.

🏝️ Benefits

• Remote work arrangement.

• Short-term contractor engagement lasting up to 24 weeks.

• Part-time engagement may be considered based on agreement.

• Weekend on-call availability.

• Flexible work location among approved eligible sites.

• Opportunity to engage in AI model training and evaluation benchmarks.