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

Hello! I’m Snehita Bhar, an AI/ML Engineer with 4+ years of experience building scalable machine learning and optimization solutions across enterprise and healthcare domains. I excel in Python, SQL, and distributed data processing, and I enjoy turning data into actionable insights through predictive modeling, feature engineering, and real-time data pipelines. I specialize in Generative AI and LLMOps, including Retrieval-Augmented Generation, prompt engineering, agentic workflows, and vector databases like Pinecone and FAISS. I design and deploy end-to-end AI systems—from data ingestion and model development to production deployment and monitoring—using Kubernetes, MLflow, Docker, and CI/CD. I’m passionate about delivering reliable, scalable AI solutions on AWS and GCP and collaborating across engineering, data, and business teams to drive impact at scale.…Hello! I’m Snehita Bhar, an AI/ML Engineer with 4+ years of experience building scalable machine learning and optimization solutions across enterprise and healthcare domains. I excel in Python, SQL, and distributed data processing, and I enjoy turning data into actionable insights through predictive modeling, feature engineering, and real-time data pipelines. I specialize in Generative AI and LLMOps, including Retrieval-Augmented Generation, prompt engineering, agentic workflows, and vector databases like Pinecone and FAISS. I design and deploy end-to-end AI systems—from data ingestion and model development to production deployment and monitoring—using Kubernetes, MLflow, Docker, and CI/CD. I’m passionate about delivering reliable, scalable AI solutions on AWS and GCP and collaborating across engineering, data, and business teams to drive impact at scale.

Snehita Bharta

AI Engineer, AI Developer, Data Scientist, +2





Hello! I’m Snehita Bhar, an AI/ML Engineer with 4+ years of experience building scalable machine learning and optimization solutions across enterprise and healthcare domains. I excel in Python, SQL, and distributed data processing, and I enjoy turning data into actionable insights through predictive modeling, feature engineering, and real-time data pipelines. I specialize in Generative AI and LLMOps, including Retrieval-Augmented Generation, prompt engineering, agentic workflows, and vector databases like Pinecone and FAISS. I design and deploy end-to-end AI systems—from data ingestion and model development to production deployment and monitoring—using Kubernetes, MLflow, Docker, and CI/CD. I’m passionate about delivering reliable, scalable AI solutions on AWS and GCP and collaborating across engineering, data, and business teams to drive impact at scale.…Hello! I’m Snehita Bhar, an AI/ML Engineer with 4+ years of experience building scalable machine learning and optimization solutions across enterprise and healthcare domains. I excel in Python, SQL, and distributed data processing, and I enjoy turning data into actionable insights through predictive modeling, feature engineering, and real-time data pipelines. I specialize in Generative AI and LLMOps, including Retrieval-Augmented Generation, prompt engineering, agentic workflows, and vector databases like Pinecone and FAISS. I design and deploy end-to-end AI systems—from data ingestion and model development to production deployment and monitoring—using Kubernetes, MLflow, Docker, and CI/CD. I’m passionate about delivering reliable, scalable AI solutions on AWS and GCP and collaborating across engineering, data, and business teams to drive impact at scale.

Available to hire

Hello! I’m Snehita Bhar, an AI/ML Engineer with 4+ years of experience building scalable machine learning and optimization solutions across enterprise and healthcare domains. I excel in Python, SQL, and distributed data processing, and I enjoy turning data into actionable insights through predictive modeling, feature engineering, and real-time data pipelines.

I specialize in Generative AI and LLMOps, including Retrieval-Augmented Generation, prompt engineering, agentic workflows, and vector databases like Pinecone and FAISS. I design and deploy end-to-end AI systems—from data ingestion and model development to production deployment and monitoring—using Kubernetes, MLflow, Docker, and CI/CD. I’m passionate about delivering reliable, scalable AI solutions on AWS and GCP and collaborating across engineering, data, and business teams to drive impact at scale.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

AI/ML Engineer at Insight Global

May 1, 2025 - Present

Architected an agentic AI platform using LLMs and LangGraph to autonomously ingest, analyze, and transform multi-modal enterprise data (audio and text) into decision-ready insights, reducing manual data processing by 65%. Designed a multi-agent orchestration framework (Planner, Retriever, Validator, Executor) enabling dynamic task decomposition and self-correcting workflows. Implemented hybrid RAG retrieval (vector, keyword, and metadata filtering) with Pinecone and FAISS, boosting contextual relevance and reducing hallucinations in downstream analytics. Integrated real-time streaming with Kafka to process 50K+ daily data events with sub-second latency. Built LLM guardrails (schema validation, toxicity filters, confidence scoring, retry logic) for enterprise reliability. Deployed services on Kubernetes (EKS) with autoscaling and created a plug-and-play API ecosystem (FastAPI) for BI integrations, accelerating decision workflows by 50%.

AI/ML Engineer at Optum

October 1, 2024 - April 1, 2025

Architected end-to-end clinical risk intelligence platform leveraging LLMs and predictive models to identify high-risk patients and recommend interventions, improving early risk detection across 500K+ patient records. Developed hybrid NLP models (transformers on clinical notes) with structured EHR data, raising AUC from 0.71 to 0.86. Implemented real-time risk scoring APIs using FastAPI, delivering sub-100ms inference for dynamic patient risk updates across care management systems handling 20K+ daily requests. Built a RAG-based clinical knowledge assistant integrating medical guidelines and historical data, reducing decision turnaround by 45%. Designed explainable AI frameworks (SHAP, LIME) to improve transparency and HIPAA-aligned interpretability. Engineered data pipelines with Spark and Airflow to improve data freshness by 60% and enable near real-time retraining. Added model monitoring and drift detection (SageMaker Monitor and custom checks) reducing performance degradation by 33%

AI/ML Engineer at Infosys

January 1, 2021 - November 1, 2023

Built an enterprise decision optimization platform leveraging machine learning and simulation to improve pricing, operations, and risk across multiple business units. Developed feature engineering pipelines on large-scale structured datasets with Python and Spark, boosting data quality and downstream model performance by 32%. Designed and deployed ensemble models (XGBoost, Random Forest) for forecasting and anomaly detection, reducing forecasting error and improving operational planning accuracy. Created automated experimentation frameworks (A/B and multivariate tests) to evaluate model-driven decisions and increase experiment velocity by 3x. Engineered real-time data processing pipelines with Kafka and Spark Streaming, enabling near real-time analytics. Developed SHAP-based explainability dashboards to improve stakeholder trust and adoption by 40%. Optimized model performance through hyperparameter tuning and cross-validation, reducing training time by 38% while improving generalizati