Harshad Golatkar
@harshadgolatkar
I design benchmarks and training data that improve LLM reasoning, reliability, and real-world agent performance.
IndiaWhat I'm looking for
I'm designing and reviewing realistic AI-agent scenarios at Mercor, creating benchmarks that test reasoning, planning, prioritization, information retrieval, and decision-making in real-world workflows.
At Turing, I evaluate complex reasoning tasks and model outputs across reading comprehension, logical reasoning, and analytical reasoning. I create high-quality reference responses, identify reasoning gaps, and support robust training datasets through quality assurance, annotation, validation, and feedback.
My work also includes computer-use and workflow annotation across DevOps, productivity, and data analytics environments, plus high-precision data annotation for robotics and gaming applications.
Before AI training, I solved engineering problems at Chegg and tested GPS/GNSS and LTE devices for Apple through Tech Mahindra. I bring a master's degree in Electrical Engineering, hands-on experience with GNSS, LTE, MATLAB, and embedded systems, and strong analytical rigor to AI evaluation.
Experience
Work history, roles, and key accomplishments
Design and maintain realistic digital environments and user personas to evaluate AI agents in complex workflows. Create benchmark scenarios assessing reasoning, planning, and decision-making, and conduct end-to-end evaluations with failure analysis.
Design and evaluate complex reasoning tasks across reading comprehension, logical reasoning, and analytical reasoning. Train and improve frontier LLMs by evaluating outputs, identifying reasoning gaps, and crafting high-quality reference responses.
Solved advanced academic and real-world engineering problems in electronics, telecommunications, and embedded systems.
Conducted technical research and validation of solutions for graduate and undergraduate topics.
Authoring solutions using LaTeX and markdown format
Worked as an on-site vendor for Apple Inc. on GPS/GNSS device testing and validation. Executed GNSS field engineering tests and analyzed receiver behavior using NMEA data and MATLAB tools.
Education
Degrees, certifications, and relevant coursework
University of Texas at Arlington
Master of Science, Electrical Engineering
Grade: 3.75/4.0
Master of Science in Electrical Engineering from the University of Texas at Arlington, completed in May 2016 with a GPA of 3.75/4.0.
Vidyalankar Institute of Technology, University of Mumbai
Bachelor of Engineering, Electronics Engineering
Grade: 67%
Bachelor of Engineering in Electronics Engineering from Vidyalankar Institute of Technology, University of Mumbai, completed in June 2013 with an overall score of 67%.
Tech stack
Software and tools used professionally
Availability
Location
IndiaAuthorized to work in
Salary expectations
Social media
Job categories
Skills
Interested in hiring Harshad?
You can contact Harshad and 90k+ other talented remote workers on Himalayas.
Message HarshadGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
