Pod Lead – Mathematics (Terminal Bench Science)

Engagement Type: Short-Term Contract (3 Weeks)
Compensation: ₹2.5 Lakh per month (pro-rated for the 3-week engagement)
Availability: 8 hours per day, with a minimum of 4 hours of overlap with Pacific Standard Time (PST)

About the Role

We are seeking an experienced Mathematics Expert / Pod Lead to lead a team of 5–10 trainers in developing high-quality, realistic, terminal-based scientific and technical tasks for Terminal Bench Science.

In this role, you will oversee the end-to-end quality of mathematics and computational science tasks, ensuring mathematical correctness, reproducibility, appropriate complexity, and reliable automated grading. You will mentor trainers, manage task quality and delivery, and ensure that benchmark tasks reflect authentic mathematical research and scientific computing workflows.

The role spans numerical and applied mathematics, scientific computing, optimization, statistics, mathematical modeling, computational algebra, and formal verification.

Key Responsibilities

- Lead, mentor, and support a pod of 5–10 trainers responsible for developing mathematical and scientific computing tasks.
- Review tasks end to end, including problem statements, datasets, execution environments, reference solutions, and automated tests.
- Verify mathematical correctness, problem well-posedness, convergence, stability, conditioning, discretization error, and edge-case handling.
- Ensure tasks require meaningful, multi-step mathematical reasoning and computational problem-solving rather than simple lookups or single-library calls.
- Validate the appropriate use of exact, symbolic, arbitrary-precision, and floating-point computations.
- Assess numerical tolerances in relation to problem conditioning and expected solution accuracy.
- Design and review automated graders using mathematical properties such as residuals, feasibility, optimality certificates, invariants, error bounds, and proof checking.
- Ensure task reproducibility through pinned dependencies, libraries, solver versions, and execution environments.




- Identify and prevent hard-coded solutions, test-data leakage, and other approaches that bypass the intended computation.
- Provide precise, actionable feedback and track trainer revisions through completion.
- Train and onboard team members on mathematical rigor, task design, coding practices, and evaluation standards.
- Allocate work, monitor quality and throughput, resolve bottlenecks, and escalate blockers when necessary.
- Maintain documentation covering task guidelines, recurring issues, quality standards, and exemplary tasks.
- Collaborate with the Mathematics Team Lead and other technical stakeholders to continuously improve benchmark quality.

Required Qualifications

- Ph.D., postdoctoral experience, or equivalent advanced expertise in Mathematics, Applied Mathematics, Statistics, or a closely related field.
- Strong programming skills in one or more of the following: Python, Julia, C/C++, MATLAB/Octave, or computer algebra systems.
- Strong Linux and command-line/terminal proficiency.
- Hands-on experience with numerical methods, scientific computing, symbolic computation, optimization, computational statistics, or mathematical modeling.
- Ability to rigorously evaluate mathematical derivations, algorithms, proofs, and computational results.
- Experience reviewing research outputs, technical code, mathematical work, or scientific computing workflows.
- Experience mentoring or leading small technical, research, or engineering teams.
- Robust written communication skills, with the ability to provide clear, constructive, and technically precise feedback.
- Ability to assess computational reproducibility, automated test reliability, and the scientific validity of technical tasks.




- Ability to commit to 8 hours per day for the 3-week contract, including at least 4 hours of overlap with PST.

Preferred Qualifications / Nice to Have

- Experience with NumPy, SciPy, SymPy, mpmath, SageMath, PARI/GP, GAP, Macaulay2, or Mathematica-style workflows.
- Experience with ODE/PDE tools such as FEniCS, Firedrake, DifferentialEquations.jl, or PETSc.
- Familiarity with optimization frameworks such as CVXPY, JuMP, Pyomo, or HiGHS.
- Familiarity with formal verification and proof assistants such as Lean/mathlib, Coq/Rocq, or Isabelle.
- Experience with Docker, Git, continuous integration (CI), and automated testing.
- Experience designing benchmarks, competition problems, or computational evaluations.
- Experience evaluating AI coding agents, reasoning systems, or terminal-based agents.
- Experience creating, reviewing, or judging mathematics olympiad or competition problems.
- Publications or open-source contributions in computational mathematics, numerical software, or formalized mathematics.
- Previous experience in AI training, data generation, technical annotation, or model evaluation programs.

Ideal Candidate Profile

The ideal candidate combines deep mathematical expertise with strong programming and scientific computing skills. You should be comfortable evaluating complex computational solutions, identifying subtle mathematical or numerical errors, and guiding a technical team toward consistent, high-quality deliverables.

You should also be comfortable working in Linux-based terminal environments, reviewing code and automated tests, and balancing technical rigor with delivery timelines.

Contract Details

- Role: Pod Lead – Mathematics (Terminal Bench Science)
- Contract Duration: 3 weeks
- Compensation Range: ₹2.5 Lakh per month, pro-rated for the contract period
- Working Hours: 8 hours per day
- Time Zone Requirement: Minimum 4-hour overlap with PST

Pay: ₹250,000.00 per month

Benefits:

- Flexible schedule
- Work from home

Education:

- Doctorate (Required)

Experience:

- Mathematics: 6 years (Required)

Work Location: Remote

📌 Mathematics Lead (India)
🏢 oak tree software solutions
📍 India