Looking for a job

Parth Kulshreshtha

@parthkulshreshtha

AI Engineer building LLM evaluation frameworks, agentic pipelines, and model serving infrastructure with vLLM, and multi-agent orchestration.

India

Message

What I'm looking for

I’m looking for a role where I can work with a strong and collaborative team, learn from experienced people. I’d like the opportunity to explore different technologies and areas of work, take on complex and meaningful problems, and broaden my experience across different roles and tech stack.

Much of my current work is on evaluating LLMs and the work they produce in the finance domain: designing the rubrics models are graded against, running the evaluations, and building the infrastructure those runs sit on. I also work on LLM-as-judge systems for grading model-written code, agentic quality pipelines that review annotation data, and reinforcement learning environments with verifiable rewards.

First author on an ACM paper on LLM-as-judge evaluation of enterprise code (AI-SQE 2026 at ICSE), and co-author on an ICML 2026 position paper on quality assurance timing in annotation pipelines.

Experience

Work history, roles, and key accomplishments

Current

Associate AI Engineer

Current

Centific

Aug 2025 - Present (1 year 1 month)

Built an LLM-as-judge framework for enterprise code evaluation, measuring performance gaps across public benchmarks and internal tasks. Developed screening systems for video annotation quality and evaluated AI agents on finance tasks.

LLM As Judge Python RLVR Azure AI Foundry RAG Ragas Kubernetes Docker PostgreSQL Redis Git GitHub

Associate Application Engineer - Intern

Centific

Oct 2024 - Jul 2025 (9 months)

Developed and optimized backend APIs using Python, Flask, and PostgreSQL, ensuring seamless data integration with frontend systems and improving system reliability. Designed and implemented scalable backend systems leveraging distributed task queues (Celery, Redis) to enable concurrent executions and improve overall system performance.

Flask PostgreSQL Celery Redis Azure Kubernetes Service CI CD Lang Chain Vector Databases

AI/ML Intern

LLMate

May 2023 - Jul 2023 (2 months)

Integrated AI into web and mobile applications across two projects, including an AI Tutor chatbot for CBSE exam preparation and a WhatsApp bot for Google Calendar scheduling. Enhanced teamwork skills and embraced new concepts.