CV

Machine Learning Engineer

• Multi-Agent System for Compliance Investigations
  • Built a production multi-agent compliance investigation system using an orchestrator, specialized LLM agents, MCP servers, and compliance policy documents to decide regulatory escalation, detect risk typologies, and generate analyst-ready narratives.
  • Owned the architecture and development of a five-part production stack including analyst frontend, gateway, queue-based engine, investigation agents, and MCP servers.
  • Reached 94% accuracy on escalation decisions, 84% on typology detection, and 80% on overall narrative quality through analyst feedback loops, error analysis, and iterative prompt tuning.

Research Fellow

• Auto Azure SDK Migration
  • Developed an LLM-based framework to automate migration of Azure SDK code to the latest API version, achieving a 50% reduction in engineering effort and saving 30 person-months annually.
  • Leveraged a hybrid approach combining symbolic code-graph analysis with LLM workflows and a refined knowledge base to streamline code generation.
• Programming with Representations (PwR)
  • Designed PwR, an AI-assisted programming system enabling non-profits without in-house engineering teams to build and maintain custom software by describing requirements in natural language.
  • Developed an LLM-based pipeline that transforms requirements into a custom domain-specific language (DSL), with a symbolic translation tool compiling the DSL into Python code. The DSL is also rendered as a visual workflow chart for transparency and easier iteration by non-technical users.
  • Open-sourced under the JugalBandi initiative and used as the foundation for JugalBandi's chatbot use cases. Code at microsoft/PwR-Studio.
• JugalBandi
  • Led JugalBandi, an initiative built on PwR enabling non-tech organizations to develop and deploy LLM-powered conversational bots. Featured in Satya Nadella's keynote talks.
  • Led the design and development of JugalBandi-Manager, a production runtime with a pluggable architecture for chat interfaces, LLM providers, vernacular language providers, and voice/TTS providers, with FSM-based conversation flows.
  • Contributed to JugalBandi-Studio, a web-based platform that transforms plain-language requirements into custom chatbots.
  • Deployed at CPGRAMS, MySchemes, and Bandhu (housing), with the open-source platform adopted by additional government and civil society initiatives.
• Dialog Systems for Government Services
  • Designed LLM-based dialog systems for government agencies including the Ministry of Law and Justice, Prime Minister's Office, and NeGD, enhancing citizens' access to public services.
  • Built a dense retrieval pipeline with LLM-driven follow-up question generation to classify citizen queries against a 14,000+ form grievance taxonomy (CPGRAMS) and resolve ambiguity before filing.
  • Developed supporting components including query rewriting, semantic search, and conversational hierarchical RAG for document-grounded responses.

Senior Data Science Engineer

• NNFetch - In House Vector Database
  • Created a dynamic recommendation platform, enhancing product discovery by blending metadata filters and partitioning with HNSW and ANNOY indexing for lightning-fast nearest product retrieval.
  • Empowered multiple data science projects with a pivotal recall set generator, adapting effortlessly to evolving metadata and delivering remarkable throughput of 1M RPM at a peak P99 latency of 20ms.
  • Delivered adaptive clustering logic, optimizing recall score and latency by extending existing indexes, enabling precise adaptation to diverse business use cases with rapidly changing metadata.

Data Science Engineer

• Personalised Search Ranking
  • Designed and developed a real-time, user-personalised search-ranking service, using long-term and short-term user features, query relevance, product attributes and dynamic product features in an XGBoost model optimised for CTR.
  • Engineered a high-performance solution for millions of users and products, leveraging Aerospike data store, SIMD-based cosine similarity processing, and ONNX Runtime for XGBoost model inferencing, delivering seamless operation at 500K RPM with a remarkable P99 latency of 30ms.
  • Proven positive impact on business metrics through AB tests, enhancing user experience and relevance at scale.
• Recommendation System
  • Engineered a versatile framework for real-time product recommendations, leveraging embedding-based features and MCDA to optimize for relevance, personalization, and real-time business metrics, and using Determinantal Point Processes (DPP) to incorporate diversity in the recommendations.
  • Scaled the system to handle throughput of 5M RPM with a P99 latency of 40ms, achieving a 19x latency reduction and an 88% annual hardware cost savings compared to the previous system.
• Machine Learning Scaling
  • Built reusable components for scaling data science models by optimizing for latency and throughput. Maintaining compatibility by python, aligning with preferences of data scientists and easy to use with minimal code changes. Proposed solutions have been adopted to improve multiple data science services at Myntra.
  • Engineered a memory-efficient solution, consolidating embedding vectors in shared memory to reduce latency by 4.5x and reduce memory footprint by 6x. Enhanced application throughput per node by enabling more worker processes per node.
  • Introduced a high-performance approach using SIMD for calculating similarity scores and re-ranking, drastically cutting computation cycles and latency. The method handles up to 15x more traffic while improving latency.
• Image Pose Detector
  • Created an scalable online service for human pose detection from an image using a ResNet-18 model with custom layers.
  • Able to handle 27x more throughput with a 6x reduction in latency from its predecessor on a single node.

Software Engineering Intern

• Developed an encoder-decoder-based generative model for preliminary image generation using Generative Adversarial Networks (GANs).
• Developed an image refinement model for processing the generated preliminary image to incorporate garment textures, ensuring accurate top-wear product replacement while retaining pose and body shape.
• The generated images were close to the Myntra image standards.

Software Developer

• Developed a music and movie recommendation system, personalised according to the preferences of multiple users in a group setting.
• Developed the backend API server responsible for serving recommendations, user and groups management and user preferance selection.

Bachelor of Technology - Computer Science and Engineering

• Relevant Courses
  • CS 13101 - Data Structures
  • CS 14101 - Analysis of Algorithms
  • CS 14103 - Computer Organization
  • CS 14104 - Automata Theory
  • CS 15101 - Microprocessor and its application
  • CS 15103 - Database Management System
  • CS 15106 - Computer Architecture
  • CS 16102 - Compiler Construction
  • CS 16105 - Computer Networks
  • CS 16103 - Data Mining

College Bot

Cloton

Distribution

Sakshatkar

Smart Ville

Sacred Bazaar

Secure Quiz

Best Industry Paper, Runner-Up at ICPE 2024

Employee of the Year 2023 at Myntra

Best Long Paper Award at Convergence 2023

Quarter Award JFM 2023

Quarter Award JAS 2023

Won Multiple accolades in several technical competitions held at different techfests

• • Winner Of Softablitz (2019, 2020) - Softablitz is the software development event organized under the annual techno-management event Avishkar at MNNIT Allahabad
  • Winner of TuxWars (2020) - TuxWars is the Linux based event organized under the annual techno-management event Avishkar at MNNIT Allahabad
  • Winner of DevJam (2019) - DevJam is the software development contest organized under Weekend Of Code by Computer Club MNNIT Allahabad

Institute Merit Scholarship

• Provided by MNNIT Allahabad to top 10% of students in the batch for excellence in academics