Jay, llm engineer

Jay

LLM Engineer

Bengaluru, India · UTC+5:30 · 13 years of experience

Jay focuses on measurable model behavior, reliable retrieval, and production evaluation.

Request a shortlist

Why this profile fits

Evaluation before optimization

Defines datasets, graders, and regression checks so model changes are measured against real failure cases.

Reliable retrieval and tool use

Improves grounding, structured outputs, tool permissions, and recovery behavior for production workflows.

Cost and latency control

Treats task success, response time, and model spend as one production system rather than separate concerns.

Relevant toolkit

PythonLangGraphClaude APIOpenAI GPT APIPostgreSQL

Delivery evidence

Selected work

Groundedness Evaluation Platform

B2B support-automation SaaS

Designed and shipped a groundedness and answer-correctness evaluation platform built from real production failure cases. The suite scores faithfulness, citation validity, and retrieval recall on every prompt and index change, and became the release gate that took the flagship assistant from 71% to 94% faithful answers.

BraintrustPython

Hybrid RAG for Legal Document Search

Legal and compliance technology

Rebuilt a citation-heavy legal search assistant using hybrid dense-plus-lexical retrieval with cross-encoder reranking. Tuned semantic chunking per document type and added groundedness checks, raising recall@5 to 91% and cutting unsupported citations by over 80% across a corpus of 2.3M clauses.

PineconeOpenAI Embeddings
View more profile detail →

Relevant experience

Career timeline

Lead LLM Engineer

2022–Present

AI product studio (enterprise RAG) · Bengaluru, India (Remote)

  • Led a RAG re-architecture for an enterprise support assistant, lifting answer groundedness from 71% to 94% and cutting cost per resolved query by 38%.

Lead Product Manager

Jan 2025–Present

ViitorCloud Technologies · On-site

  • Product Manager for two AI-powered SaaS products at ViitorCloud Technologies driving roadmap, prioritization, and end-to-end delivery alongside my Tech Lead responsibilities.

Senior Software Engineer

May 2021–Present

ViitorCloud Technologies · Bengaluru, India

  • Built learning-to-rank models (LambdaMART) that improved top-3 result relevance by 19% across enterprise search deployments.

Skill depth

Show experience in context.

VerbalCommunicationDomainUnderstandingProblemSolvingCodeQualitySystemDesignDeliverySpeed
Competency shapeAssessment across the same six dimensions used for every profile.

Relevant experience by skill

Python13 years
Information Retrieval & Search11 years
NLP & Embeddings9 years
FastAPI6 years
Vector Databases5 years
RAG Systems5 years
LLM Evals4 years
Prompt Engineering4 years
See the complete skill index

Languages

PythonTypeScriptSQLGoJava

Frameworks

FastAPILangGraphLangChainDjangoFlask

Libraries/APIs

Claude APIOpenAI APIGemini APICohere RerankSentence-TransformersHugging Face TransformersPydanticInstructor

Tools

BraintrustLangSmithOpenAI EvalsGuardrailsDockerGitWeights & Biases

Paradigms

Retrieval-Augmented GenerationHybrid SearchSemantic ChunkingEval-Driven DevelopmentTool CallingStructured OutputsHuman-in-the-loop

Platforms

AWSGCPAzure OpenAIDatabricksKubernetes

Storage

pgvectorPineconeQdrantElasticsearchRedisPostgreSQL

Other

MLOpsObservability & TracingCost OptimizationPrompt Versioning

Education

Formal background

Bachelor of Technology (B.Tech), Computer Science and Engineering

National Institute of Technology, Tiruchirappalli · 2009–2013 · First Class with Distinction

Executive Post Graduate Program, Machine Learning and Artificial Intelligence

International Institute of Information Technology, Bangalore · 2017–2018

Credentials

Certifications

NVIDIA-Certified Associate: Generative AI LLMs

NVIDIA · 2023 · Certified

AWS Certified Machine Learning Engineer – Associate

Amazon Web Services · 2022 · Certified

Communication

Languages

English

Fluent

Tamil

Native

Hindi

Professional

More examples

Similar LLM Engineer profiles.