Skip to main content
HimalayasHimalayas logo
Harika sriHS
Open to opportunities

Harika sri

@harikasri

AI Evaluation Specialist and Statistical Researcher improving frontier models with RLHF, SxS evaluation, and rigorous stats.

India
Message

What I'm looking for

I’m looking for a role where I can apply RLHF/SFT evaluation rigor—building calibrated rubrics, detecting hallucinations, and improving reliability and fairness with statistical foundations and clear guideline-driven workflows.

I’m an AI Evaluation Specialist and Statistical Researcher with 7+ years spanning government statistical research and frontier AI model evaluation. I bring deep expertise in RLHF and SFT, rubric design and calibration, hallucination detection, CoT validation, and multilingual NLP—so evaluations translate into measurable reliability, fairness, and real-world performance.

I’ve delivered consistently across AfterQuery, Turing, and Mercor—maintaining 100% guideline adherence and 99% on-time delivery while executing Side-by-Side (SxS) assessments and structured fact-checking. In parallel, I’ve built statistically rigorous workflows: from digitizing service records for ~10 lakh government employees and cutting reporting time by 40%, to forecasting revenue using ARIMA, tax buoyancy, logarithmic regression, and consensus forecasting with sub-₹30 crore error on an ₹87,000 crore base.

Experience

Work history, roles, and key accomplishments

AE

Document Artifact Expert

AfterQuery Experts

Apr 2026 - May 2026 (1 month)

Produced high-quality document artifacts (PPTX, DOCX, PDF, XLSX) for large-scale AI training data collection. Applied evaluation standards to ensure artifact quality and instructional alignment for frontier model development.

ME

Vibe Coder & STEM OCR

Mercor

Nov 2025 - Mar 2026 (4 months)

Designed atomic rubrics (8–12 tags) with calibrated difficulty levels to train models for client-side web application tasks. Validated vision-language outputs, repaired OCR-extracted STEM pairs with standardized LaTeX, and authored golden responses and multi-turn RLHF conversations under structural constraints.

II

Data Annotator & Content Moderator

Innodata Inc

Nov 2025 - Dec 2025 (1 month)

Performed SFT annotation and refinement tasks for ML pipelines. Improved AI-generated text for fluency, bias elimination, and PII compliance while following annotation requirements.

CE

Assistant Statistical Officer

CEGIS

Aug 2019 - Oct 2025 (6 years 2 months)

Led digitisation of service records for ~10 lakh government employees across 29 departments and 199 Heads of Department. Architected Telangana’s Digital Workforce Repository, reducing reporting time by 40% and building time-series forecasting models (ARIMA, tax buoyancy, regression, consensus forecasting) including sub-₹30 crore error on an ₹87,000 crore base.

ON

AI Data Evaluator (Hindi/English)

OneForma

Jun 2024 - Aug 2024 (2 months)

Ran RLHF comparative ranking (SxS) evaluations of AI responses in Hindi and English. Assessed response accuracy and cultural nuance to support multilingual model reliability improvements.

Education

Degrees, certifications, and relevant coursework

Indian Institute of Technology Kanpur logoIK

Indian Institute of Technology Kanpur

Master of Science in Statistics, Statistics

2016 - 2018

Earned an M.Sc. in Statistics from IIT Kanpur.

Osmania University logoOU

Osmania University

Bachelor of Science, Mathematics, Statistics & Computer Science

2014 - 2016

Completed a B.Sc. in Mathematics, Statistics & Computer Science at Osmania University.

Find your dream job

Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan