Nancy Sinha profile photo 1 on Tal

Nancy Sinha

Data Scientist @Qualitykiosk | AI Intern @Bosch | VIT’25

Bengaluru

2+ years of work experience

QualityKiosk Technologies
Aug 20251 yr 3 mosPresent

Bengaluru, Karnataka, India

Bosch Global Software Technologies
Sep 202410 mosJun 2025

Bengaluru, Karnataka, India

Built a Responsible AI evaluation framework to assess LLMs on fairness, robustness, explainability, and compliance. Developed a GenAI-based benchmarking toolkit using metrics like fairness, contextual relevance, prompt alignment, and G-Eval. Designed an Agentic AI evaluation system focused on KPIs like success rate, steps per task, and HITL frequency. Contributed to multiple GenAI POCs, enhancing robustness using RAGAS and DeepEval. Created a multi-agent ad generation platform using LangGraph + LangChain, with a Supervisor agent routing tasks across 8 specialized agents. Built LLMOps observability tools (Traces, Prompt Dashboards, Metrics), and improved LLM outputs via prompt calibration.

Nancy’s AI Stack

claude code
claude code
cursor
cursor
hugging face
hugging face
mistral
mistral
ollama
ollama
openai
openai

Education

Vellore Institute of Technology

Integrated MTech, CSE with Specialization in Data Science

Vellore Institute of Technology

20205 yrs2025

Join Nancy and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Nancy Sinha on Tal

Headline

Data Scientist @Qualitykiosk | AI Intern @Bosch | VIT’25

Location

Bengaluru

AI stack

claude code

cursor

hugging face

mistral

ollama

openai

Work experience

Data Scientist at QualityKiosk Technologies, Aug 2025 - Present · 1 yr 3 mos, Bengaluru, Karnataka, India

Artificial Intelligence Intern at Bosch Global Software Technologies, Sep 2024 - Jun 2025 · 10 mos, Bengaluru, Karnataka, India, Built a Responsible AI evaluation framework to assess LLMs on fairness, robustness, explainability, and compliance. Developed a GenAI-based benchmarking toolkit using metrics like fairness, contextual relevance, prompt alignment, and G-Eval. Designed an Agentic AI evaluation system focused on KPIs like success rate, steps per task, and HITL frequency. Contributed to multiple GenAI POCs, enhancing robustness using RAGAS and DeepEval. Created a multi-agent ad generation platform using LangGraph + LangChain, with a Supervisor agent routing tasks across 8 specialized agents. Built LLMOps observability tools (Traces, Prompt Dashboards, Metrics), and improved LLM outputs via prompt calibration.

Education

Integrated MTech, CSE with Specialization in Data Science, Vellore Institute of Technology

Nancy Sinha - Data Scientist in Bengaluru | Tal