PRANJAL JINDAL
AI EngineerAI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI Engineer with less than a year in LLM evaluation, NLP, and competitive programming.
AI Evaluation Specialist with experience in designing and authoring competitive programming problems, developing comprehensive test cases, and reviewing coding challenges for clarity and correctness. Skilled in analyzing real-world software repositories to pinpoint functional issues and authoring detailed evaluation rubrics for LLM code reasoning capabilities. Expertise includes evaluating LLM responses for truthfulness, reasoning, writing quality, and factual accuracy, providing structured feedback for model improvement. Proven ability in building NLP pipelines for duplicate question detection and developing multi-agent AI research systems with LangChain and custom AI agents for advanced information processing and report generation.
USICT, IPU
B.Tech · Computer Science and Engineering (AI)
N/A – June 30, 2024
Mercor
Agentic Code QA Writer (Contract)
May 1, 2026 – Present
India
AirDawg Labs
AI Evaluation Specialist (Task-based)
April 1, 2026 – April 30, 2026
India
Mercor
Competitive Coding Writer (Contract)
January 1, 2026 – May 31, 2026
India
Duplicate Question Pair Detection
June 25, 2026 – Present
• Built an NLP pipeline to detect semantically duplicate questions across 30,000+ question pairs. • Engineered 23+ features, including TF-IDF similarity, cosine similarity, and lexical overlap metrics. • Implemented and tuned an XGBoost classifier, achieving 80% classification accuracy.
View ProjectMulti-Agent AI Research System
June 25, 2026 – Present
• Developed a multi-agent AI research automation system using LangChain, enabling autonomous web search, information extraction, analysis, and report generation. • Designed specialized AI agents including Search Agent and Reader Agent with tool-calling capabilities using Tavily API for real-time web retrieval and BeautifulSoup for webpage scraping. • Implemented state-based agent workflow to store and pass research context between multiple agents, improving structured information processing. • Built Writer and Critic chains to generate, evaluate, and refine research reports through iterative LLM-based feedback before producing final outputs.
View ProjectBronze Medal in Mathematics Olympiad (IMO)
Unknown
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's academic projects and contract roles demonstrate a proactive and self-driven approach to learning and applying AI concepts. Their involvement in competitive programming and LLM evaluation roles suggests a strong interest in technical challenges and continuous improvement, which aligns well with a culture of innovation and excellence. The diversity of projects, from NLP to multi-agent systems, indicates adaptability and a broad interest in the AI domain.
Soft Skills & Operational Fit
The candidate demonstrates strong analytical and problem-solving skills through their work in competitive programming problem design and LLM evaluation. Their experience in designing detailed evaluation rubrics and providing structured feedback indicates attention to detail and a methodical approach. The multi-agent system project highlights an ability to design complex workflows and integrate various tools, suggesting good operational fit for roles requiring system design and integration.