Headline

Data Engineering Specialist | Demand Intelligence Platforms | Distributed Systems | AI Orchestration | LLM Fine-tuning | GenAI Automation

About

I build the data and intelligence backbone for large-scale talent intelligence systems, working at the intersection of data engineering, applied machine learning, and AI-driven reasoning. Currently, I am developing a demand aggregation platform that consolidates hiring signals from job boards, career sites, and other external sources across ~8.9 lakh companies. This involves ingesting high-volume, multi-source datasets and transforming unstructured and semi-structured data into a standardised, queryable format — at a scale exceeding 300 million records. On the Engineering side, I design and implement scalable, fault-tolerant data pipelines using distributed processing frameworks, with a strong emphasis on low latency, production readiness, and multi-dimensional data modelling. This includes batch and near real-time processing, workflow orchestration, data partitioning, and storage optimisation to ensure pipelines are reliable, performant, and cost-efficient. I also build production-grade scraper engines with modular adapter patterns, anti-detection, and lifecycle tracking to handle large-scale web data acquisition. On the AI and data science side, my work spans the full applied AI spectrum — from fine-tuning domain-specific LLMs and building RAG pipelines to designing multi-prompt LLM chains and hybrid enrichment workflows that combine algorithmic cleaning with batch LLM processing at scale. This includes model-in-the-loop systems for entity resolution, job taxonomy classification, skill extraction, demand signal normalisation, compensation intelligence, and record linkage — problems that sit at the boundary of structured data engineering and applied NLP. Beyond pipelines, I build analytics and BI layers that translate raw intelligence into enterprise-ready outputs — dashboards, automated reports, and benchmarking tools that product and business teams actually use. I spend most of my time thinking about system design, data modelling, and performance optimisation, and I am particularly interested in building systems where AI is not a bolt-on but a core processing layer deeply integrated into the data pipeline itself. I work cross-functionally with product, AI, and analytics teams to translate evolving requirements into scalable, production-grade data systems.

Location

Bengaluru

AI stack

hugging face

langchain

langgraph

ollama

Work experience

Data Engineer at HireSense.ai, Mar 2025 - Present · 1 yr 3 mos, Bengaluru, Built a large-scale demand aggregation platform capturing hiring signals across job boards, career sites, and web sources, covering ~8.9 lakh companies and 300M+ records. Infrastructure & Engineering Built a production-grade scraper engine with modular ATS adapters, proxy integration, anti-detection, rate limiting, and structured output validation. Implemented job lifecycle tracking with deduplication, delist detection, and historical snapshot versioning. Developed scalable ETL/ELT pipelines with parallel ingestion, fault tolerance, and schema standardisation Implemented entity resolution, deduplication, and data standardisation pipelines for company, role, and skill-level mapping. Designed batch and near real-time processing with workflow orchestration, data partitioning, and storage optimisation. Applied AI & LLM Engineering Architected a custom AI orchestration layer for large-scale semantic enrichment — entity resolution, job title normalisation, skill extraction, and demand signal classification. Designed a multi-prompt LLM chain for automated talent intelligence reports, Master Prompt for taxonomy, Normalisation Prompt for candidate mapping, Observation Prompts for insights Built a Streamlit-based tool enabling non-technical SMEs to generate AI-powered intelligence reports without coding. Built a compensation intelligence pipeline, archetype lookup, skill clustering, salary percentiles, skill premium analysis, and automated report generation. Developed a hybrid LLM enrichment pipeline combining algorithmic cleaning with batch LLM processing at scale. Fine-tuned domain-specific LLMs with measurable accuracy gains over zero-shot baselines. Analytics & BI Built Power BI dashboards for talent analytics, compensation benchmarking, and competitor intelligence for enterprise clients. Delivered an end-to-end telecom churn prediction model integrating data extraction, predictive modelling, and BI reporting

Analyst at Enstoa, Oct 2022 - Oct 2023 · 1 yr 1 mo, Remote, - Designed and implemented Power BI dashboards for tracking ticket statuses and priorities across multiple clients, reducing reporting time by 25%. - Maintained and optimized numerous BIP reports using SQL, enhancing data accuracy by 20%. - Collaborated with solution teams on report development and work orders, improving project delivery timelines by 15%. - Streamlined customer issue resolution processes, achieving a 95% resolution rate within SLA timelines.

Junior Analyst at Enstoa, Nov 2021 - Oct 2022 · 1 yr, Bengaluru, Karnataka, India, - Addressed complex data issues and provided client-facing solutions using Power BI and SQL. - Delivered ad-hoc analysis and visualizations, enhancing decision-making capabilities for clients. - Served as the primary point of contact for BI problem resolution, achieving a 98% client satisfaction rate.

Data Science Intern at INNODATATICS * Innovation | Data | Analytics, Mar 2021 - Apr 2021 · 2 mos, Bengaluru, Karnataka, India

Education

Bachelor of Engineering - BE, Information Science and Engineering, SDM INSTITUTE OF TECHNOLOGY (SDMIT), UJIRE