Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Spandan Maaheshwari, an AI/ML Engineer with 4+ years of experience building GenAI pipelines, multi-agent LLM systems, and RAG architectures to automate enterprise workflows. I specialize in model fine-tuning, scalable API deployment, and orchestration of ETL/ML pipelines, unifying data engineering, LLMOps, and real-time inference to drive accuracy, efficiency, and insights across cross-functional teams. Currently, I’m the Founding AI Engineer at PredictaBio Innovations in Boston, where I lead end-to-end GenAI initiatives in biotech, streamline data integration and dashboard explainability, and maintain high-availability inference services. I enjoy collaborating with biology and data teams to turn complex data into actionable insights and scalable solutions.…Hi, I’m Spandan Maaheshwari, an AI/ML Engineer with 4+ years of experience building GenAI pipelines, multi-agent LLM systems, and RAG architectures to automate enterprise workflows. I specialize in model fine-tuning, scalable API deployment, and orchestration of ETL/ML pipelines, unifying data engineering, LLMOps, and real-time inference to drive accuracy, efficiency, and insights across cross-functional teams. Currently, I’m the Founding AI Engineer at PredictaBio Innovations in Boston, where I lead end-to-end GenAI initiatives in biotech, streamline data integration and dashboard explainability, and maintain high-availability inference services. I enjoy collaborating with biology and data teams to turn complex data into actionable insights and scalable solutions.

Spandan Maaheshwari

AI Engineer, Data Scientist, Full Stack Developer, +5





Hi, I’m Spandan Maaheshwari, an AI/ML Engineer with 4+ years of experience building GenAI pipelines, multi-agent LLM systems, and RAG architectures to automate enterprise workflows. I specialize in model fine-tuning, scalable API deployment, and orchestration of ETL/ML pipelines, unifying data engineering, LLMOps, and real-time inference to drive accuracy, efficiency, and insights across cross-functional teams. Currently, I’m the Founding AI Engineer at PredictaBio Innovations in Boston, where I lead end-to-end GenAI initiatives in biotech, streamline data integration and dashboard explainability, and maintain high-availability inference services. I enjoy collaborating with biology and data teams to turn complex data into actionable insights and scalable solutions.…Hi, I’m Spandan Maaheshwari, an AI/ML Engineer with 4+ years of experience building GenAI pipelines, multi-agent LLM systems, and RAG architectures to automate enterprise workflows. I specialize in model fine-tuning, scalable API deployment, and orchestration of ETL/ML pipelines, unifying data engineering, LLMOps, and real-time inference to drive accuracy, efficiency, and insights across cross-functional teams. Currently, I’m the Founding AI Engineer at PredictaBio Innovations in Boston, where I lead end-to-end GenAI initiatives in biotech, streamline data integration and dashboard explainability, and maintain high-availability inference services. I enjoy collaborating with biology and data teams to turn complex data into actionable insights and scalable solutions.

Available to hire

Hi, I’m Spandan Maaheshwari, an AI/ML Engineer with 4+ years of experience building GenAI pipelines, multi-agent LLM systems, and RAG architectures to automate enterprise workflows. I specialize in model fine-tuning, scalable API deployment, and orchestration of ETL/ML pipelines, unifying data engineering, LLMOps, and real-time inference to drive accuracy, efficiency, and insights across cross-functional teams.

Currently, I’m the Founding AI Engineer at PredictaBio Innovations in Boston, where I lead end-to-end GenAI initiatives in biotech, streamline data integration and dashboard explainability, and maintain high-availability inference services. I enjoy collaborating with biology and data teams to turn complex data into actionable insights and scalable solutions.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Javanese

Advanced

Bashkir

Advanced

Work Experience

Founding AI Engineer at PredictaBio Innovations

January 1, 2025 - November 18, 2025

Pioneered a multi-agent GenAI system using LangChain, LangGraph, and OpenWebUI with custom router agents to classify user intents and route tasks to GPT-4 powered analytics modules, expanding automated insights across enterprise data by 80%. Streamlined text-to-SQL conversational agent pipelines with automated schema normalization, anomaly detection, and Pinecone-backed RAG context injection, cutting data integration errors by 90% and accelerating dashboard delivery by 40%. Fine-tuned LLMs (T5, Mistral, Claude) to improve protein-sequence classification accuracy by 32%, built scalable ETL pipelines in PySpark and AWS Glue to process 3 TB+ genomic datasets with HIPAA/HL7 compliance; created explainable AI dashboards (SHAP, LIME) and deployed containerized services with Docker/Kubernetes; sustained >99.9% availability.

Research Engineer at Institute for Experiential AI

March 1, 2024 - March 1, 2024

Established a scalable RAG pipeline using Azure Data Factory, ADLS Gen2, Unity Catalog, and Databricks, automating ~10k document ingestions into Delta Lake and improving embedding similarity by 81% via LLaMA-2 70b. Deployed a real-time chatbot REST API using Streamlit, Kubernetes-based Lakehouse monitoring, leveraging Azure DevOps CI/CD with 120+ unit tests and MLflow to evaluate toxicity, readability, and minimize model hallucinations.

Machine Learning Engineer at Tridhya Tech

August 1, 2022 - August 1, 2022

Architected a personalized recommendation system for hotels and flights, leveraging FAISS for candidate generation and Transformers for learning-to-rank, resulting in a 25% increase in CTR. Integrated Spark SQL with Amazon Redshift and Cassandra to retrieve historical user behaviour and real-time session data, reducing data processing time by 60%. Explored reinforcement learning techniques (UCB, Thompson Sampling) to optimize content exploration, boosting user discovery of relevant hotel options by 20%. Conducted A/B testing and built interactive Tableau dashboards to visualize CTR, engagement, and conversion trends, leading to a 15% improvement in user engagement. Designed and implemented a scalable MLOps pipeline with GitHub CI/CD, Docker, and Kubernetes, automating model workflows (training and testing), cutting deployment time by 70% and reducing production issues by 50%. Mentored junior engineers on ML pipeline design and data governance best practices, improving team delivery vel

Machine Learning Engineer at Tridhya Tech

July 1, 2019 - August 1, 2022

Architected a personalized recommendation system for hotels and flights using FAISS for candidate generation and Transformers for learning-to-rank, achieving a 25% increase in CTR. Integrated Spark SQL with Amazon Redshift and Cassandra to retrieve historical user behavior and real-time session data, reducing data processing time by 60%. Developed RL-inspired exploration techniques (Upper Confidence Bound, Thompson Sampling) to boost user discovery by 20%. Conducted A/B tests and built Tableau dashboards to visualize CTR, engagement, and conversion, improving user engagement by 15%. Designed a scalable LLM evaluation framework with ROUGE, BLEU, perplexity, and domain-specific metrics, boosting model quality by 25%. Optimized models for inference via quantization, pruning, beam search, fast ANN, and distillation, cutting size by 75%, latency by 60%, and costs by 40% with 98% accuracy retained. Led ML Ops pipelines with GitHub CI/CD, Docker, and Kubernetes, automating training/testing, r

Research Engineer at Institute for Experiential AI

November 1, 2023 - March 1, 2024

Established a scalable RAG pipeline using Azure Data Factory, ADLS Gen2, Unity Catalog, and Databricks, automating ~10k document ingestions into Delta Lake and improving embedding similarity by 81% via LLaMA-2 70b. Deployed a real-time chatbot REST API using Streamlit, with Kubernetes-based Lakehouse monitoring and Azure DevOps CI/CD with 120+ unit tests; evaluated toxicity and readability to minimize model hallucinations using MLflow.