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

AI/ML engineer focused on building production-grade LLM systems, retrieval/agentic workflows, and reliable ML pipelines across Kubernetes and cloud platforms. Experienced in LLM evaluation, RAG quality improvements, and governance using model monitoring and Bedrock Guardrails. Strong background in anomaly detection, scalable data engineering, and MLOps with MLflow, plus engineering automation and integrations. Passionate about turning complex ML/LLM problems into measurable, dependable systems that scale to real users.…AI/ML engineer focused on building production-grade LLM systems, retrieval/agentic workflows, and reliable ML pipelines across Kubernetes and cloud platforms. Experienced in LLM evaluation, RAG quality improvements, and governance using model monitoring and Bedrock Guardrails. Strong background in anomaly detection, scalable data engineering, and MLOps with MLflow, plus engineering automation and integrations. Passionate about turning complex ML/LLM problems into measurable, dependable systems that scale to real users.

Riddhi Ketan Shah

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





AI/ML engineer focused on building production-grade LLM systems, retrieval/agentic workflows, and reliable ML pipelines across Kubernetes and cloud platforms. Experienced in LLM evaluation, RAG quality improvements, and governance using model monitoring and Bedrock Guardrails. Strong background in anomaly detection, scalable data engineering, and MLOps with MLflow, plus engineering automation and integrations. Passionate about turning complex ML/LLM problems into measurable, dependable systems that scale to real users.…AI/ML engineer focused on building production-grade LLM systems, retrieval/agentic workflows, and reliable ML pipelines across Kubernetes and cloud platforms. Experienced in LLM evaluation, RAG quality improvements, and governance using model monitoring and Bedrock Guardrails. Strong background in anomaly detection, scalable data engineering, and MLOps with MLflow, plus engineering automation and integrations. Passionate about turning complex ML/LLM problems into measurable, dependable systems that scale to real users.

Available to hire

AI/ML engineer focused on building production-grade LLM systems, retrieval/agentic workflows, and reliable ML pipelines across Kubernetes and cloud platforms. Experienced in LLM evaluation, RAG quality improvements, and governance using model monitoring and Bedrock Guardrails.

Strong background in anomaly detection, scalable data engineering, and MLOps with MLflow, plus engineering automation and integrations. Passionate about turning complex ML/LLM problems into measurable, dependable systems that scale to real users.

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

Intermediate

Intermediate

Intermediate

Language

Aragonese

Advanced

Javanese

Advanced

Work Experience

Backend Engineer - AI Platform at Qlik

June 1, 2025 - Present

Built and operated multiple production AI services for large-scale users. Evaluated multi-agent workflows using LangSmith traces and LLM-as-a-judge metrics to improve hallucination/tool selection/trajectory pass rates from 45% to 85% (serving 30K+ users). Implemented hybrid OpenSearch retrieval (keyword + embeddings) with semantic reranking, improving NDCG@5 by 45% on a domain evaluation set. Managed reliability using Kubernetes Deployments and horizontal pod autoscaling to sustain a 99% availability SLO. Modernized legacy systems with an LLM-assisted COBOL-to-Java pipeline using AST parsing and Neo4j dependency graphs, migrating 20 modules with a 95% functional-test pass rate. Added AI governance via Bedrock Guardrails and custom security scanners for image/PDF validation, reducing p95 validation latency by 40% using parallel execution.

AI Engineer at Qlik

June 1, 2025 - Present

Standardized reusable LLM evaluation workflows for Qlik’s agentic platform using evaluation datasets, success metrics, and benchmarking with LangSmith and Langfuse, improving reliability and output quality for 30K+ users. Built an internal operations assistant leveraging MCP-based connectors, Grafana/Splunk telemetry, RAG retrieval, and Jira actions to automate SLO reporting and platform-support queries, reducing response and incident triage time by 80%. Developed and deployed a modular RAG pipeline with LangChain, hybrid retrieval, reranking, secure MCP connectors, and access-aware retrieval, improving enterprise knowledge-query relevance by 45%. Designed multimodal input validation in the LLM Gateway and Go microservices using AWS Bedrock Guardrails and custom validators, enabling secure request handling while reducing inference latency by 40%. Created reproducible foundation-model experimentation workflows with A/B testing, prompt evaluation, failure analysis, and trace-based revi

AI/ML Engineer at Qlik

June 1, 2025 - Present

Led improvements to Qlik Answers (AI Assistant) by enhancing LLM response accuracy for 30K+ global users. Integrated LangSmith and Arize Phoenix into the agentic system to boost observability and reliability; developed hybrid RAG pipelines with LangChain and OpenSearch, including a reranker to improve domain-specific query relevance; architected multimodal input support in LLM Gateway and microservices with security scanning, reducing inference latency; automated LLM experiments with A/B testing across models (GPT-4, Claude, Mistral) improving model selection efficiency; created a test-generation agent with GitHub Copilot to automate Python/Go test writing, achieving 100% coverage.

Machine Learning Engineer at Synechron (Client: American Express)

November 1, 2023 - May 1, 2025

Designed and delivered production ML and data systems. Built an XGBoost-based anomaly detection pipeline processing 10K+ daily transactions, reaching 82% precision and reducing false positives by 30%. Developed scalable Elasticsearch ingestion pipelines to transform 200K+ customer records into versioned, reproducible feature datasets for batch training and evaluation. Implemented MLOps workflows with MLflow to track experiments, model metrics, and feature-drift statistics across 15+ inputs, enabling reproducible comparisons and regression detection. Built full-stack components (React + backend APIs) for an M&A analysis tool including document review and financial analysis. Fine-tuned pretrained LLMs using Hugging Face Transformers and PEFT/LoRA, evaluating task-specific quality metrics and validation/train divergence.

Machine Learning Engineer at Synechron|Client: American Express

November 1, 2023 - May 31, 2025

Developed and deployed an anomaly-detection system for large-scale financial data using XGBoost, EDA, and feature engineering, reducing false positives by 35% for downstream risk-review workflows. Built scalable PySpark and Airflow data pipelines processing 200K+ customer records, enabling reproducible ML workflows, automated batch training, and versioned model releases. Applied SHAP interpretability and MLflow experiment tracking to explain model predictions, compare model versions, and improve transparency for stakeholders. Adapted domain-specific LLMs using Hugging Face and LoRA/PEFT, evaluating validation loss, overfitting behavior, and response quality to improve precision by 45% on proprietary data. Deployed ML and LLM services as containerized REST APIs, integrating versioned inference workflows with reusable service interfaces for downstream applications.

Machine Learning Engineer at Synechron

November 1, 2023 - May 1, 2025

Architected an end-to-end ML pipeline for fraud detection with automated feature engineering, processing 10K+ daily transactions; developed an ensemble fraud detection model (Isolation Forest, LOF, XGBoost) achieving 82% precision with 30% reduction in false positives; implemented MLflow-based monitoring for model accuracy and data drift across 15+ features; fine-tuned LLMs (LoRA/QLoRA) on proprietary data and built RAG pipelines with vector search to boost domain-specific query precision by 45%.

Software Developer Intern at Cisco

May 1, 2023 - August 31, 2023

Developed a Python integration layer between network simulation and routing-validation systems, improving test orchestration and reducing manual setup time by 30% across 500+ routing configurations. Improved validation throughput using Python multithreading and structured test workflows, enabling automated scale testing across 1,000+ simulated network topologies.

Software Development Engineer II Intern at Cisco

May 1, 2023 - August 1, 2023

Built a Python integration layer connecting network simulation and routing systems, reducing test setup time by 30% and enabling automated validation of 500+ routing configurations; improved large-scale Lisp network simulation throughput by 40% through multithreaded Python, enabling parallel testing of 1000+ topologies.

Machine Learning Engineer Intern at Applied Cloud Computing (Startup)

November 1, 2019 - December 1, 2019

Built recommendation and deployed ML inference services on AWS. Developed a SageMaker object2vec recommendation model over 20K+ user-item interactions, achieving 0.70 Precision@10 on a held-out evaluation set. Deployed the model to a SageMaker endpoint, using S3 for data and model artifact storage.

Machine Learning Engineer Intern at Applied Cloud Computing

November 1, 2019 - December 1, 2019

Developed a collaborative filtering movie recommendation system on AWS SageMaker using Object2Vec, achieving 70% precision@10 on 20K+ user-movie interactions; deployed the model as a REST API on AWS EC2 with an automated data pipeline from S3 for real-time personalized recommendations.