Akshay Dongare

Co-Founder

Raleigh, North Carolina, United States1 yr 2 mos experience

AI EnabledAI ML Practitioner

Key Highlights

Developed production-ready AI systems for global organizations.
Created an open-source package with over 725,000 downloads.
Led chatbot development for blood donor education in Kenya.

Stackforce AI infers this person is a Generative AI Engineer with a strong focus on open-source development and healthcare applications.

Contact

Skills

Core Skills

Large Language Models (llm)Open-source DevelopmentRetrieval-augmented Generation (rag)Model Compression

Other Skills

LangGraphLangfuseLiteLLMLangSmithCommunity OutreachLangChainTensorFlowKerasPython (Programming Language)AI AgentsContinuous Integration and Continuous Delivery (CI/CD)PyPiPoetryGithub ActionsWeb Services API

About

For professional engagements, reach me at: 📩 contact@akshaydongare.com I build production-ready AI systems. My experience includes work with global organizations like ISO and Harvard University.

Experience

1 yr 2 mos

Total Experience

1 yr 2 mos

Average Tenure

1 yr 2 mos

Current Experience

Iso - international organization for standardization

Applied AI Engineer

May 2025 – Aug 2025 · 3 mos · Geneva, Switzerland · Remote

LangChainLangGraphLangfuseLiteLLMAI AgentsLangSmith+2

Langchain-litellm

Creator & Maintainer

Apr 2025 – Present · 1 yr 2 mos · Raleigh, North Carolina, United States · Remote

Scaled 'langchain-litellm' to 725,000+ downloads, an open-source package I created and maintain.
Establishes a key community integration for developers building with diverse LLM providers.
Manage all aspects: feature development, CI/CD pipeline (GitHub Actions & Poetry), issue tracking, and community engagement.
GitHub: https://github.com/akshay-dongare/langchain-litellm
PyPI: https://pypi.org/project/langchain-litellm/

LangGraphLangfuseLiteLLMLangSmithCommunity OutreachLarge Language Models (LLM)+10

Langchain

Open Source Contributor

Apr 2025 – Present · 1 yr 2 mos · San Francisco Bay Area · Remote

Merged PRs improving versioning, dependency isolation, and import paths for the community ecosystem.
Authored official integration guides used by thousands of developers.
Contributions: github.com/langchain-ai/langchain/pulls?q=is%3Apr+author%3AAkshay-Dongare+

LangChainLarge Language Models (LLM)AI AgentsContinuous Integration and Continuous Delivery (CI/CD)PyPiPoetry+4

Harvard university

Generative AI Engineer

Jan 2025 – May 2025 · 4 mos · Cambridge, Massachusetts, United States · Remote

Led the end-to-end development of a production WhatsApp chatbot using LLM-based RAG systems to support blood donor education for Damu Sasa, a blood services management platform by Jiji Health, deployed across Kenya under Amref Health Africa
Designed retrieval and grounding workflows over official WHO blood donation guidelines to ensure medically accurate, policy-aligned, and Kenya-specific responses
Implemented safety, validation, and personalization logic to adapt outputs to user-specific eligibility constraints while preventing harmful or misleading guidance
Worked closely with Harvard GAMI, Project Prana Foundation, and Amref Health Africa stakeholders to deliver a closed-beta system validated in real operational contexts

Large Language Models (LLM)Retrieval-Augmented Generation (RAG)LLM Guardrails

Mercor

Generative AI Engineer

May 2023 – May 2023 · 0 mo · San Francisco, California, United States · Remote

Developed core components of an LLM-powered Educational Testing Platform, integrating and testing various LLMs and vector databases during early commercial adoption of GenAI tools while industry standards were still emerging
Collaborated with Stanford PhD AI researcher through daily technical exchanges to implement and optimize RAG solutions and custom LLM guardrails, directly contributing to product architecture and MVP delivery, incorporating cutting-edge techniques in prompt engineering through systematic A/B testing to improve LLM response quality

Large Language Models (LLM)Prompt EngineeringPinecone Vector DatabaseRetrieval-Augmented Generation (RAG)LLM Guardrails

Blue heron research partners

AI/ML Optimization Feedback Contributor (Venture Capital Due Diligence)

Oct 2022 – Oct 2022 · 0 mo · New York, New York, United States · Remote

Participated in a targeted technical consultation to evaluate Neural Magic's (aquired by Red Hat) pruning/quantization technologies for VC investors, providing hands-on implementation insights from Tech Mahindra's model optimization project
Delivered user experience feedback on their DeepSparse library during a 30-minute expert interview session informing investment research

Tech mahindra

Deep Learning Intern

May 2022 – Aug 2022 · 3 mos · Pune, Maharashtra, India · On-site

Implemented TinyML optimization techniques on YOLOv5 object detection models for deployment on resource-constrained edge devices for data privacy and low-latency inference
Achieved 12x model size reduction and 10x faster CPU inference through combined application of pruning and INT8 quantization while maintaining detection accuracy on the COCO dataset

TinyMLModel CompressionPruningQuantization