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

AI Engineer with 5+ years of experience building production-grade agentic systems and LLM-powered automation. Skilled in orchestrating agent workflows, prompt/tool calling, RAG systems, and evaluation/benchmarking to improve reliability and reduce regressions. Experience integrating AI agents with GitHub, ticketing systems, and CI/CD pipelines, along with strong background in data engineering and cloud infrastructure. AWS-certified (ML Specialty and MLOps), focused on secure, observable, production-ready engineering.…AI Engineer with 5+ years of experience building production-grade agentic systems and LLM-powered automation. Skilled in orchestrating agent workflows, prompt/tool calling, RAG systems, and evaluation/benchmarking to improve reliability and reduce regressions. Experience integrating AI agents with GitHub, ticketing systems, and CI/CD pipelines, along with strong background in data engineering and cloud infrastructure. AWS-certified (ML Specialty and MLOps), focused on secure, observable, production-ready engineering.

YAGNESH CH

AI Engineer, Data Scientist, Full Stack Developer, +7





AI Engineer with 5+ years of experience building production-grade agentic systems and LLM-powered automation. Skilled in orchestrating agent workflows, prompt/tool calling, RAG systems, and evaluation/benchmarking to improve reliability and reduce regressions. Experience integrating AI agents with GitHub, ticketing systems, and CI/CD pipelines, along with strong background in data engineering and cloud infrastructure. AWS-certified (ML Specialty and MLOps), focused on secure, observable, production-ready engineering.…AI Engineer with 5+ years of experience building production-grade agentic systems and LLM-powered automation. Skilled in orchestrating agent workflows, prompt/tool calling, RAG systems, and evaluation/benchmarking to improve reliability and reduce regressions. Experience integrating AI agents with GitHub, ticketing systems, and CI/CD pipelines, along with strong background in data engineering and cloud infrastructure. AWS-certified (ML Specialty and MLOps), focused on secure, observable, production-ready engineering.

Available to hire

AI Engineer with 5+ years of experience building production-grade agentic systems and LLM-powered automation. Skilled in orchestrating agent workflows, prompt/tool calling, RAG systems, and evaluation/benchmarking to improve reliability and reduce regressions.

Experience integrating AI agents with GitHub, ticketing systems, and CI/CD pipelines, along with strong background in data engineering and cloud infrastructure. AWS-certified (ML Specialty and MLOps), focused on secure, observable, production-ready engineering.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Beginner

Language

English

Fluent

Work Experience

AI Engineer at University of Florida

August 1, 2025 - Present

Designed and implemented agent workflows integrating with GitHub, CI pipelines, documentation, and deployment tools, including codebase-aware retrieval, task planning, prompt orchestration, and tool calling. Built agents that open pull requests, generate tests, summarize releases, and request approval for sensitive changes using robust permission models, approval states, audit logs, evaluation, and rollback procedures, achieving 94% task completion rates. Developed RAGAS-based and custom benchmarking/evaluation suites to measure agent quality and reliability, reducing regression issues by 41%. Collaborated with engineering teams across 12+ departments to prototype, iterate, and reduce manual review effort by 42%, while implementing secure coding practices and production monitoring with Prometheus and Grafana.

ML Engineer at Accenture USA

August 1, 2025 - Present

Built and deployed AI-powered web applications using Django and TypeScript/React, delivering end-to-end solutions that reduced manual analysis time by 60% for non-technical users. Architected AI Agent workflows using LangGraph and OpenAI function calling, enabling users to interact with complex data through intuitive conversational interfaces. Designed and integrated RAG pipelines with vector stores into production systems, enabling semantic search and grounded LLM responses with source attribution. Built scalable backend infrastructure on AWS (EC2, ECS, Lambda, S3) and Postgres, ensuring high availability and performance for 10k+ daily active users. Implemented CI/CD pipelines with automated testing and deployment, maintaining code quality and enabling rapid feature iteration in a collaborative remote environment.

Senior ML Engineer at S&P Global

May 1, 2022 - July 31, 2024

Built and deployed production AI agents for financial intelligence, integrating agent workflows with internal APIs, ticketing systems, and CI/CD pipelines to automate code review, testing, and documentation across 50+ enterprise accounts. Developed codebase-aware retrieval and task planning modules using LangChain and vector databases (Weaviate). Implemented automated review flows with permission models, approval states, and audit logs, reducing manual code review time by 34% while meeting security and compliance requirements in regulated environments. Created benchmarking suites using MLflow for experiment tracking and evaluation, establishing quality gates that reduced hallucination-driven errors by 34% before production deployment. Worked with client engineers to gather requirements, prototype solutions, and ensure secure, reliable, maintainable systems.

ML Engineer at S&P Global India

May 1, 2022 - July 1, 2024

Developed full-stack AI applications with Python, Django, and JavaScript, integrating machine learning models into web platforms for financial document intelligence. Built and deployed AI Agent solutions that automated data extraction and analysis, reducing processing time from 30 minutes to under 3 minutes per document. Collaborated with product stakeholders to translate business requirements into technical deliverables, delivering robust, scalable systems on AWS. Optimized backend performance and database queries, improving application response times by 35% through code refactoring and caching. Stayed current with emerging AI/ML technologies, recommending and implementing improvements that enhanced product capabilities and user experience.

Data Engineer at Uber

June 1, 2020 - May 31, 2022

Owned large-scale distributed systems processing 2M+ events/sec using Apache Spark and Kafka, including CI/CD pipelines, deployment, and incident response for real-time ML feature computation across 100TB+ daily datasets. Built event-driven architectures and REST APIs using Go and Python to integrate with engineering workflow automation tools (GitHub, ticketing, deployment). Implemented CI/CD pipelines with automated testing, static analysis, and code review automation, reducing pipeline failures by 41% and enabling production deployment practices with 99.9% reliability. Designed and maintained permission models, audit logs, and rollback procedures for production systems to ensure secure and reliable operations across engineering and data science teams.

ML Data Engineer at Uber India

June 1, 2020 - May 1, 2022

Designed scalable data pipelines and backend services using Python, TypeScript/Node.js, and Postgres, supporting real-time ML feature computation for 50+ production models. Built and maintained cloud infrastructure on AWS and GCP, implementing deployment best practices that ensured 99.9% uptime for critical AI services. Developed RESTful APIs and microservices using FastAPI and Node.js, enabling seamless integration of ML models into web applications and internal tools. Implemented comprehensive monitoring and observability with Prometheus and Grafana, ensuring system reliability and enabling rapid troubleshooting.