Avinash P.

AI Researcher

Pune, India12 yrs 3 mos experience

Most Likely To SwitchAI ML Practitioner

Key Highlights

Expert in LLM applications and AI technologies.
Led successful data science teams with high accuracy models.
Innovative speaker and community leader in AI.

Stackforce AI infers this person is a Senior AI Engineer specializing in LLM and Machine Learning applications.

Contact

Skills

Core Skills

Large Language Models (llm)Artificial Intelligence (ai)Natural Language Processing (nlp)Machine LearningData Science

Other Skills

NLPMultimodal chatbotsMulti-agent systemsOrchestrationEntity matchingDeep learningMulti-language modelsEmbedding size reductionSearch ranking signalsEntity resolutionBlocking techniqueData analysisSearch rankingReinforcement LearningEnd-to-End ML pipeline

About

What I do - Currently I am working as a Senior AI Engineer at Nvidia with focus on LLM based applications including multimodal chatbots, multi-agent systems, orchestration, etc. Work Tech - Worked on LLM based ReAct agents, A2A, MCP protocols worked on NLP, Large Language Models (LLMs) (seq2seq, LSTMs, BERT, XLNET, entity matching, etc) worked on vision - object detection worked on retail data (millions of records) - likelihood to buy, likelihood to pay full price etc models My talks 1. A2A protocol (https://www.analyticsvidhya.com/datahacksummit-2025/sessions/agent-to-agent-protocol-benefits-and-workflows?utm_source=blog&utm_medium=navbar) 2. ReAct based LLM agents (https://www.analyticsvidhya.com/datahacksummit-2024/speakers/avinash-pathak) 3. Entity Matching using NLP (https://www.youtube.com/watch?v=0CaHZuzzeHI) 4. Prompt engineering techniques 5. Basics of LLMs 6. Search using ML 7. Time complexity of ML models 8. How ML models are stored and how to use them 9. GPT4 architecture 10. ML design - a restaurant recommendation system 11. The world of diffusion 12. Embeddings Compression 13. Stable Diffusion Models I host a community of like-minded data scientists https://www.meetup.com/pune-deep-learning-club/ where more than 5k individuals come together for talks.

Experience

Nvidia

Senior AI Engineer

Oct 2023 – Present · 2 yrs 5 mos · Pune, Maharashtra, India · On-site

I work on LLM and LLM Agents for use cases like chatbots, GUI generation, Database Assistant, and other use cases.
I worked on Autogen, Langchain, LangGraph, MCP Server, Various LLMs, Finetuning, Distillation, etc.
I also have patents in GenAi area.

Large Language Models (LLM)NLPMultimodal chatbotsMulti-agent systemsOrchestrationArtificial Intelligence (AI)

Tomtom

Lead Data Scientist

Feb 2022 – Oct 2023 · 1 yr 8 mos

Leading a team of data scientists at TomTom
Few of the projects that I am working on
● POIs (Point of Interests) deduplication based on entity resolution
Trained deep learning-based entity matching/deduplication model with >97% accuracy for English speaking countries where each country has more than a million entities
Used blocking technique to reduce number of computationally expensive computations (time reduction by a factor for 10X)
Adopted multi-language models for non-English speaking countries (Experiment with BLOOM language model)
Working on embedding size reduction - Sentence Transformers, Autoencoder etc.
● Improved entities name matching
Improved name matching by 5% using Sentence Transformers (BERT based uncased)
● Search Ranking Signals
Analyzed footfall data for places in Netherlands
Created a signal (confidence score) which is one of the parameters for deciding the ranking of place search in TomTom map
● Metric for Routing Points (Routing points make correlation between places and streets on TomTom maps)
Created a metric for RP on new TomTom maps by comparing with older version
The extension of same project is creating metric considering ground truth data

Entity matchingDeep learningMulti-language modelsEmbedding size reductionSearch ranking signalsNatural Language Processing (NLP)+1

Acquia

Staff Machine Learning Engineer

Jan 2021 – Feb 2022 · 1 yr 1 mo · Pune, Maharashtra, India

Propensity Models like Likelihood to Buy, Likelihood to Convert, Likelihood to pay full price for retail with 95% score accuracy, worked on data of more than 3 years. Millions of data points per company.
Reinforcement Learning model for send time optimisation
Worked on End-to-End ML pipeline
Skills: Python, Spark, Qubole, Machine Learning, Reinforcement Learning, Tensorflow, AWS, Reinforcement Learning

Machine LearningReinforcement LearningEnd-to-End ML pipelinePropensity Models

Embold technologies gmbh

2 roles

Team Lead ML Research

Promoted

Nov 2020 – Jan 2021 · 2 mos

Leading ML on code with the use of various Machine Learning techniques.
Code fix recommendation
Designed model architectures based on SOTA language models and Graph NNs to perform code analysis.
Constructed datasets to benchmark code analysis tasks such as bug localization & code recommendation.
Designed CoFEx (Code Feature Extraction) model and managed its integration with the Gamma Recommendation Engine
Managed the model training for downstream tasks such as code auto-completion, bug detection and localization.
Worked on TFIDF, LSTMs, Seq2Seq, RNNs, and transformer models (BERT and XLNET)

Machine Learning techniquesCode analysisModel architecture designMachine Learning

Senior Machine Learning Research Engineer

Feb 2019 – Nov 2020 · 1 yr 9 mos

Working on machine learning-based static analysis of code.

Nvidia

2 roles

Senior System Software Engineer

Sep 2017 – Jan 2019 · 1 yr 4 mos

Worked on occupancy calculation considering resources like threads, register files, shared memory, constant bank, texture memory to determine if Compiler has produced optimal code
Developed a framework for frame-based GPU performance/functionality verification
Verified synchronization done in Nvidia Compiler using assembly language code
Texture/Surfaces verification and framework development in CUDA/OpenCL for the same
CUDA Memory Consistency Model Verification (which is based on C++ 11 memory model)
Verified all the instructions added to PTX assembly for all the architectures from Kepler onwards
Wrote a framework for assembler verification from scratch
Wrote optimal tests in Assembly language (closest assembly language to Nvidia GPU which is directly translated to GPU binary)
Mentored an intern for project “Generating automatic tests for Compiler synchronization
verification” in Python; we generated 45 tests from 8 seed tests with isomorphic graph approach and generalised it later to create huge automated test corpus