Open to opportunities

AASHIK User

@aashikumar

AI engineer specializing in LLM evaluation and conversational AI systems, improving reasoning quality through validation.

India

Message

What I'm looking for

I’m looking for a role where I can lead LLM evaluation and conversational AI development—building multi-turn and tool-calling workflows, then validating structured outputs for correctness, safety, and real-world reliability.

I’m an AI Engineer focused on LLM evaluation and conversational AI workflows. I help teams assess reasoning quality, validate response accuracy, and ensure structured outputs hold up in real assistant scenarios.

In my current role (Dec 2024–Present), I design and evaluate multi-turn conversations and tool-calling/function-calling workflows. I evaluate outputs for correctness, coherence, contextual understanding, and safety—using JSON workflows, API-driven logic, and rigorous response validation to improve reliability.

I also bring practical product-building experience from projects and freelance work, including backend API development and data-oriented experimentation. For example, I worked on “Optimizing Hyperparameters with Pelican Algorithm for Deep Learning-based Oral Cancer Detection,” which strengthened my ability to connect model behavior with measurable performance outcomes.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Turing

Dec 2024 - Present (1 year 6 months)

Worked on LLM evaluation projects focused on reasoning quality, response validation, and conversational AI behavior. Designed multi-turn conversations and tool-calling workflows and evaluated outputs for correctness, coherence, contextual understanding, and safety.

LLM Evaluation Prompt Engineering Validation Python REST APIs