Krishnkant Swarnkar

AI Researcher

New York, New York, United States6 yrs 6 mos experience

Most Likely To SwitchHighly Stable

Key Highlights

Expert in developing AI-driven market research tools.
Proficient in Natural Language Processing and Machine Learning.
Strong background in deep learning frameworks and model training.

Stackforce AI infers this person is a SaaS-focused AI Engineer with expertise in Natural Language Processing and Machine Learning.

Contact

Skills

Core Skills

Machine LearningNatural Language Processing

Other Skills

Model TrainingData ScienceDeep LearningRetrieval-Augmented Generation (RAG)Large Language ModelsAgentic FrameworksText SummarizationInformation ExtractionSoftware DevelopmentCompetitive CodingCC++AlgorithmsData StructuresPython

About

An AI / NLP enthusiast, passionate about advancing AI / building value through software. I enjoy working working in agile settings, collaborating to create value, exploring new technologies, and continuously learning new skills and enhancing the existing. Hit me a dm if you'd like to chat/connect. My current work focuses on developing market research tools utilizing cutting-edge AI techniques, including Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Agentic Frameworks, and Natural Language Processing (NLP) to solve complex problems efficiently. Skills and Experience: • Programming Languages: Python, C++, SQL, Java (basic), C# (Basic) • Deep Learning Frameworks: PyTorch, TensorFlow, HuggingFace Transformers, Keras, Theano • Development Frameworks: Elasticsearch, Django, LangChain, asyncIO • Development Tools: Cursor, VSCode, Pycharm, Android Studio, Git • Cloud & Deployment Tools: Kubernetes, Docker, Bedrock, Prometheus, Grafana, Git, CI/ CD • Key Interests: Large Language Models, Agentic Frameworks, Retrieval Augmented Generation (RAG), Natural Language Processing (NLP), Data Analysis, Text Summarization, Information Extraction, Software Development

Experience

6 yrs 6 mos

Total Experience

2 yrs 2 mos

Average Tenure

4 yrs 11 mos

Current Experience

Alphasense

2 roles

Senior AI Engineer

Jan 2026 – Present · 4 mos

AI Research Engineer

Jun 2021 – Jan 2026 · 4 yrs 7 mos

Market Research Chat Assistant System: Developed various key components of AlphaSense Conversational Market Research Copilot Agent built on a RAG pipeline utilizing frontier LLMs, including planning, natural language understanding, citations, guardrails, etc.
Document Summarization: Implemented document/ company summarization for Earnings/ Non-Earnings Call Transcripts, utilizing a RAG style architecture with prompt engineering on LLMs (like llama-2).
M&A Detection: Extracted Merger and Acquisition information from Press and News documents using Transformer based models, making use of Named Entity Recognition, and Entity Linking.
Company Topics Extraction: Working on extracting and ranking trending topics that describe what various business documents talk about for any given company.
Boilerplate Language Detection: Released a hybrid machine learning and heuristic based approach to detect boilerplate language in Broker Research documents.
KPI-centric Knowledge Extraction: Experimented with and deployed a BERT based language model for extracting KPI-centric information (KPI, Amount, Time, etc.) from Event Transcripts & Press Releases, achieving significant improvements over the existing Rule Based models.

Machine LearningModel TrainingData ScienceNatural Language Processing

College of information and computer sciences, umass amherst

2 roles

Graduate Student Researcher

Promoted

Aug 2020 – May 2021 · 9 mos · Amherst, Massachusetts, United States

Advisor: Prof. Liangliang Cao
Adversarial Robustness for Visual Question Answering Systems.

Machine LearningModel Training

Graduate Student Researcher

Jan 2020 – May 2020 · 4 mos · Amherst, MA, USA

[Information Extraction and Synthesis Lab (IESL), UMass ]
Project: De-biasing Contextualized Word Embeddings
Advisor: Prof. Andrew McCallum
Industrial Mentorship: Lexalytics

Machine LearningModel Training

Bosch

Natural Language Understanding Intern

May 2020 – Aug 2020 · 3 mos · Sunnyvale, California, United States

I as a part of NLU team,
Developed state of art deep learning models for "Intent Detection and Slot filling".
Developed and analyzed a BERT based novel method for the task which beat all the prior models on two public datasets (SNIPS and ATIS)
Additionally, contributed to the ongoing research on NLU disambiguation for speech data (ASR).
Submitted a research paper (under review).

Machine LearningModel TrainingNatural Language Processing

Technische universität darmstadt

Research Internship

May 2018 – Nov 2018 · 6 mos · Darmstadt, Germany

[Ubiquitous Knowledge Processing (UKP) Lab, TU Darmstadt]
(May'18-July'18)
Analyzed the shortcomings of existing cross lingual approaches used for cross lingual question retrieval in programming domain
(Source: German, Target: English) and proposed two extensions to improve them:
1. by enhancing the translation quality using Monolingual cQA data,
2. by improving the robustness of SoTA question retrieval model to common translation errors.
Work published at WWW 2019.
(July'18 - Nov'18): Remote collaboration
Proposed and experimented with various ways for attacking NLP models (by generating visually inspired adversaries) and making them robust against such attacks.
Work published at NAACL 2019.

Machine LearningModel Training

Indian institute of technology (banaras hindu university), varanasi

Research Internship

May 2017 – Jul 2017 · 2 mos · Varanasi, Uttar Pradesh, India

[NLP Research Lab, IIT (BHU) Varanasi]
Worked on a Pipeline Based Question Answering System which transforms unstructured data (text) to structured representations
beforehand and finds the answer to the given queries by exploiting graph-matching based algorithms, dependency relations
and hand crafted rules.
Exposure: Dependency Grammar, Wordnet, Conceptual Graphs, Verbnet, Knowledge Based Semantic Role Labelling, Transformational Analysis.

Model Training