Looking for a job

UTKARSH TIWARI

@utkarshtiwari2

Message

I build production AI platforms, RAG systems, multi-agent workflows, and scalable ML infrastructure.

India

Message

What I'm looking for

I'm looking to build reliable, production AI products involving generative AI, agentic workflows, RAG, ML infrastructure, and cloud-native deployment, with opportunities to optimize latency, cost, and user experience.

I've built production AI systems at Streamingo, including RAG pipelines, multi-agent platforms, LLM evaluation frameworks, and end-to-end MLOps workflows for enterprise documentation and customer support.

I fine-tune open-source Qwen models with PEFT, LoRA, and QLoRA for efficient on-premise inference, and optimize GPU workloads through CUDA tuning, Kubernetes, and parallelized inference workflows. My work reduced daily processing time by five hours and helped reduce annual cloud costs by 10–12%.

At VoerEir AB, I led AI/ML initiatives from design through deployment, built LSTM predictive models and production RAG platforms, and improved cloud performance by 20%. I also developed LLM evaluation metrics, Kubernetes workload tooling, and secure credential storage.

Earlier at Quantive, I built a high-speed web scraping library, LLM-powered RAG automation, and distributed pipelines processing more than 3 million product documents daily. I enjoy building reliable AI products that improve latency, cost, and user experience.

Experience

Work history, roles, and key accomplishments

Current

Data and ML Engineer

Current

Streamingo

May 2025 - Present (1 year 4 months)

Built and deployed production RAG pipelines using LangChain, enabling enterprise document retrieval and context-aware reasoning. Designed a multi-agent AI platform using Google ADK and LangGraph, and implemented MLOps pipelines for training, inference, and deployment.

Lang Chain LangGraph Google ADK PEFT QLoRA Qwen fastAPI Docker Kubernetes Helm GCP GKE GCS CUDA YOLO MLOps CI CD Jenkins Bitbucket Python SDK Development

Member of Technical Staff 1 (MTS-1)

VoerEir AB

Aug 2023 - May 2025 (1 year 9 months)

Developed evaluation frameworks and quality metrics for LLM applications, tracking accuracy, latency, and failure cases. Created a Kubernetes Job launcher to manage cloud workloads and improved RESTful API design and testing workflows.

LLM Evaluation Kubernetes REST APIs Security Python Network Protocol Analyzers

Senior Member of Technical Staff 2 (MTS-2)

VoerEir AB

Aug 2023 - May 2025 (1 year 9 months)

Led AI/ML initiatives from design through deployment, shaping product direction and scalability. Designed predictive models using LSTM and deployed a production RAG platform with retrieval optimization and evaluation workflows.

RAG PEFT LLM Fine tuning Prompt Engineering Evaluation Python Machine Learning AI ML

Software Development Engineer (SDE)

Quantive (Greendeck)

Jan 2022 - Jul 2023 (1 year 6 months)

Built a custom web scraping library and an LLM-powered automation platform using RAG to streamline knowledge extraction. Designed and maintained distributed data pipelines processing over 3 million product documents daily.

Web Scraping RAG LLM Python Airflow Distributed Systems Design Patterns Data Pipelines