Open to opportunities

Sushma Jakku

@sushmajakku

Message

AI/LLM engineer applying prompt engineering and LLM evaluation to build production-grade generative AI systems.

India

Message

What I'm looking for

I’m seeking to apply analytical rigor and LLM domain knowledge to an AI Engineer role building production-grade AI systems—using LLM evaluation, prompt engineering, and RAG while collaborating across teams.

I’m an AI/ML-focused engineer with 2+ years of combined experience across data science, data analytics, and AI/LLM roles. At Innodata, I contribute to production AI/LLM workflows by designing, testing, and refining prompts, then using systematic analysis to improve output accuracy, relevance, and consistency across diverse use cases.

I validate AI/LLM outputs with data analytics techniques to identify hallucinations, factual errors, bias, and inconsistencies, supporting model evaluation and quality benchmarking. I also build structured evaluation reports and scorecards, maintain well-documented version-controlled datasets for reproducibility, and collaborate with AI researchers to calibrate annotation guidelines—alongside AWS-based analytics and end-to-end data science work (including recommendation systems and NLP projects).

Experience

Work history, roles, and key accomplishments

Current

Analyst – AI/LLM Engineer

Current

Innodata Inc

Jun 2025 - Present (1 year 1 month)

Designed and refined prompts for large language models and evaluated outputs for accuracy, relevance, consistency, and error patterns. Led high-accuracy annotation and produced dataset evaluation scorecards to support model benchmarking and downstream improvements.

Prompt Engineering LLM Output Evaluation Hallucination Detection Excel Sheets Cross Functional Collaboration

AWS Data Analytics – Virtual Internship

AICTE Eduskills

Apr 2024 - May 2025 (1 year 1 month)

Performed AWS-based data collection, cleaning, and analysis to identify trends, anomalies, and actionable insights. Built dashboards and predictive analyses and documented data pipelines to support reproducibility.

AWS Data Analytics Data Collection Data Cleaning Data Analysis Data Visualization Tableau Power BI Excel Statistical Analysis predictive modeling Data Integrity Data Pipelines

Data Science – Internship

Acmegrade

May 2023 - Mar 2024 (10 months)

Built a movie recommendation engine in Python using content-based and collaborative filtering. Conducted preprocessing, feature engineering, model comparisons, and visualized results to validate recommendation quality.