Remote Engineering Expert

About the Role

Your Mission

You will create complex, multi-constraint tasks where AI agents must interpret requirements, navigate trade-offs, configure open-source simulation tools (e.g., ngspice, PySpice, OpenFOAM), diagnose failures, and iterate toward valid solutions. You will analyze agent execution logs to expose systemic reasoning gaps and build automated graders.

Key Responsibilities

• Model-Breaking Problem Design: Author original engineering design tasks with competing constraints and explicit optimization targets.
• Simulation Integration: Build, run, and validate environments using open-source tools and custom Python test benches.
• Trajectory Analysis & Failure Diagnostics: Evaluate coding agent outputs to identify failure modes like misinterpreting feedback or physically impossible geometries.
• Cross-Functional Collaboration: Partner with AI researchers, pod leads, and domain experts (from India and globally) to integrate rigorous benchmarks into the evaluation pipeline.

Requirements

• Educational Background: Master's degree or PhD in Electrical, Mechanical, Aerospace Engineering; or equivalent experience. A Bachelor's with extensive practical experience is also accepted.
• Simulation Tooling: Proficiency with open-source packages like ngspice, FEniCSx, Gmsh, python-control, etc., combined with strong Python scripting skills.
• Evaluation Expertise: Hands-on experience with modern LLMs/coding agents and concepts like pass@k, failure-mode analysis, and nondeterministic behavior.

Engagement Details

This is a contractor role. While the commitment required is 40 hours per week (including overlap with PST), part-time engagement models are acceptable. Weekend on-call availability may be necessary depending on project needs. You will need a personal desktop/laptop and stable high-speed internet.

Career Path