Open to opportunities

Keshav Joglekar

@keshavjoglekar

Message

AI & LLM expert turning prompt design and evaluation into reliable, production-ready agentic systems.

Indonesia

Message

What I'm looking for

I’m looking to build production-grade AI/LLM systems—prompt frameworks, RAG, and evaluation pipelines—that are accurate, safe, and measurable, collaborating with teams that value iteration, benchmarking, and reliability.

I’m an AI and LLM expert with a software engineering background, specializing in prompt engineering, model output evaluation, and agentic systems. I design RAG-enhanced prompt frameworks and evaluate outputs for accuracy, reasoning quality, tone, and safety across frontier models.

As the founder of Psylent Systems, I ship production AI automation for real businesses—building workflows that resolve up to 80% of client inbound with monitoring and error handling for 24/7 reliability. I also connect RAG and tool-calling to CRMs, email, and databases across 1,000+ integrations, and scale multilingual content generation with built-in quality review.

Previously, at Storynest.ai, I joined as the first employee and helped scale the platform from 200K to 1M+ user signups while authoring prompting frameworks across story, character, comic, and education features. I also architected a multi-model backend across Claude, Replicate, OpenAI, Llama, and Grok at 98% uptime.

I bring a strong evaluation mindset from my consulting work—benchmarking 15+ AI models per quarter, compressing evaluation cycles from 6 weeks to 10 days. I’ve delivered measurable impact by improving output precision by 15% and forecast accuracy by 40%, and by cutting validation cycles by 46% through MCP integration roadmaps and technical documentation.

Experience

Work history, roles, and key accomplishments

Current

Founder, AI Engineer

Current

Psylent Systems

Feb 2026 - Present (4 months)

Engineers AI prompts and LLM agents for Claude, OpenAI, and Gemini, evaluating outputs for accuracy, tone, and reliability before deployment. Built production AI automation that resolves up to 80% of client inbound and designed RAG/tool-calling workflows integrating 1,000+ CRM, email, and database systems.

Prompt Engineering LLM Output Evaluation RAG Tool calling Agentic Systems Production AI Systems Python TypeScript

AI Automation Architect

Springbolt Group, LLC

Jul 2025 - Feb 2026 (7 months)

Evaluated and benchmarked 15+ AI models and tools per quarter for output quality, accuracy, and task fit, reducing evaluation cycles from 6 weeks to 10 days. Built RAG-enhanced prompt frameworks across Claude, OpenAI, Gemini, Llama, and Grok, improving output precision by 15% and forecast accuracy by 40%, and delivered 3.7x ROI on AI investment.

LLM Output Evaluation Benchmarking RAG Forecasting Quality Technical Documentation Python

AI Product Manager & Prompt Engineer

Storynest.ai

Aug 2024 - May 2025 (9 months)

Authored prompting frameworks for story generation, character creation, comic development, and education tools. Architected a multi-model backend (Claude, Replicate, OpenAI, Llama, Grok) at 98% uptime and scaled the platform from 200K to 1M+ user signups.

Prompt Engineering Model Routing Reliability Engineering Claude OpenAI Replicated

Cybersecurity Specialist

Grey Labs

Jan 2019 - Jan 2021 (2 years)

Built an automated phishing-simulation and security-awareness training pipeline across the enterprise using KnowBe4. Ran design-thinking workshops and prototypes that delivered 700K EUR in cost savings.

Security Awareness Training KnowBe4 Cybersecurity Design Thinking Risk reduction Workshop Facilitation

Software Developer

Grey Labs

Jan 2016 - Jan 2017 (1 year)

Led a 4-person team building a multinational web application spanning 7 cities and 2 countries. Delivered features using Python, Java, AngularJS, and MySQL as part of a broader software engineering effort.

Team Leadership Web Application Development Python Java AngularJS MySQL SQL Software Engineering

Education

Degrees, certifications, and relevant coursework

University College Dublin

Master of Science, Digital Innovation

2018 - 2019

Grade: 2:1 Honours

MSc in Digital Innovation with postgraduate research and applied innovation across technology, product, and emerging systems. Graduated with a 2:1 Honours.