Rohan Chandani

Create your portfolio with ProoV
ProoV
DE Verified work portfolio

ProoV Portfolio

Rohan Chandani

Astro and Particle Physics · University of Tübingen

View the ProoV leaderboard

Projects

Certified

Self-directed project

Energy and Renewable: Machine Learning for the Power Grid

Junior Machine Learning Engineer · AI / ML · August 2026

84/ 100

A ProoV case study · educational project, not employment

Built an end-to-end TEY predictor for a gas turbine using leakage-free sensor features and a genuine time-based holdout. Compared a LinearRegression baseline with a tuned RandomForest, then evaluated the final model on held-out data with MAE, RMSE, R2, and a residual read. Also wrote a concise model card explaining intended use, excluded leakage features, limitations, and drift monitoring.

Graded against

  • Build and validate the model correctly35%
  • Optimize and evaluate honestly25%
  • Write the Model Card (clarity + honesty)25%
  • Explain it to a non-expert15%

Passed · pass mark 60/100

What stood out6
  • Correctly dropped CO and NOx because they are downstream emission outputs not available at prediction time.
  • Used an earlier-years/later-years split to keep the test set genuinely held out.
  • Reported held-out MAE, RMSE, and R2 for the tuned forest and compared it against a linear baseline.
  • Noted residual behavior and acknowledged that strong R2 does not prove generalization beyond this plant.
  • Leakage-Free Feature Selection
  • Honest Time-Based Evaluation
The work I submitted20 tasks

12 tasks · 13 lines · Python, JavaScript · 8 written answers · 480 words

  • Problem Frame163 characters
  • Leakage Flags113 characters
  • Train Validate BaselinePython · 1.4k characters
  • Train Validate Forest943 characters
  • Tune Evaluate SetupPython · 1.5k characters
  • Tune Evaluate ResidualsPython · 2 lines
  • Tune Evaluate130 characters
  • Residual Read299 characters
  • Drift Monitor93 characters
  • Train Validate124 characters
  • Model Card838 characters
  • Teach BackJavaScript · 714 characters
  • Problem Frame12 words
  • Leakage Flags1 word
  • Train Validate Baseline141 words
  • Train Validate Forest76 words
  • Tune Evaluate Setup110 words
  • Tune Evaluate Residuals92 words
  • Tune Evaluate1 word
  • Residual Read47 words

Summarised on purpose — the submitted code and writing stay private so this page cannot be reused as an answer key. The full submission sits behind the verified certificate.

Verified certificateTamper-proof · issued by ProoV
Certified

Self-directed project

AI-Assisted Code Modernization with IBM

Junior Software Engineer · Software Engineering · August 2026

92/ 100

Based on a public IBM case study · not affiliated with IBM

Built a working modernization of the KM-Waechter repo end to end: fixed the service-wear calculation, handled missing service readings safely, repaired the nightly report, corrected the helper mileage conversion bug, and added the missing regression test. They also wrote a data-driven breakdown-risk analysis and documented the agent review process in NOTES.md, showing careful verification rather than blind trust.

Graded against

  • Fix and extend the repo with the agent35%
  • Diagnose the bug20%
  • Direct and audit the AI agent25%
  • Explain it like an engineer20%

Passed · pass mark 60/100

What stood out6
  • Caught and fixed the quiet fleet_utils.km_to_miles conversion bug that no test directly covered
  • Added the missing report test for a car with no last_service_km and verified the report no longer crashes
  • Kept the 15000 km interval and 80% threshold unchanged in both code and settings.cfg while modernizing the surrounding style
  • Produced an analyze.py that explicitly checks the data instead of assuming odometer_km and age_years are predictive
  • Leakage-Free Bug Diagnosis
  • Verified Acceptance Checking
The work I submitted20 tasks

12 tasks · 1.9k characters · 8 written answers · 117 words

  • Division Predict74 characters
  • Diagnose Line130 characters
  • Diagnose Why67 characters
  • Scope Prompt66 characters
  • Audit Findings158 characters
  • Audit Why358 characters
  • Acceptance Checklist177 characters
  • Bob Trial Click74 characters
  • Bob Ready60 characters
  • Template Repo Click82 characters
  • Verify Report71 characters
  • Exec Pitch592 characters
  • Division Predict1 word
  • Diagnose Line10 words
  • Diagnose Why11 words
  • Scope Prompt1 word
  • Audit Findings1 word
  • Audit Why65 words
  • Acceptance Checklist27 words
  • Bob Trial Click1 word

Summarised on purpose — the submitted code and writing stay private so this page cannot be reused as an answer key. The full submission sits behind the verified certificate.

Verified certificateTamper-proof · issued by ProoV
2Projects completed
2Verified certificates
88Average score
Create your portfolio with ProoV