Vishit Jiwane

Vishit Jiwane

Open to AI engineering roles in London, ideally in financial services or insurance.

AI engineer in London. I build LLM agents, document pipelines and voice systems that run in production.

AI-generated voice
Ask my AI

Vishit's AI

Answers from my verified notes

Hi, I'm Vishit's AI. I answer from his verified project notes, so I won't make things up. Ask about anything he has built, paste a job description to see where he fits, or book a call with him.

What the AI looked up

Before answering, the AI checks his notes. Each check appears here.

  1. Waiting for a question.

Ask my AI

It answers from my verified project notes, shows you every lookup it makes, and can book a call on my calendar.

Track record

2
hackathons won
3 years
of experience building software and AI
1,100+
users on GulfSafe
Novessa Pitchside's control room: five agents and their answer times
Pitchside's control room: every agent, its checks and its answer time.

Selected work

  1. EasyHunt

    Financial services. Title due diligence for home loans. Tech lead at Encegen AI Labs, team of three

    Bank lawyers in India check a property's title by reading scanned land records. EasyHunt reads them for the lawyer and drafts the report. It takes up to 20 documents per case (7/12 extracts, mutation records, sale deeds), in several languages and some handwritten, and produces a scrutiny report in the bank's own template for the lawyer to review and approve.

  2. Voice agent platform

    Voice AI. Multi-tenant phone agents. Team lead at Encegen AI Labs, owner of the voice pipeline

    Businesses create voice agents, give them a phone number and a knowledge base, and get the call logs. It is built in the style of Retell AI, and every customer's data is isolated in its own workspace.

  3. Novessa Pitchside: a goal for Ashford Rovers with the agents' explanation
    Novessa Pitchside

    Agents. Microsoft x Premier League "Inside the Game" developer hackathon. GitHub

    A personalised live football broadcast, built for the Microsoft x Premier League hackathon. A team of AI agents decides which moments matter, explains them for each viewer in their language, and proves every number before it airs.

  4. The GulfSafe dashboard: a 3D globe of the Gulf with live risk levels per country
    GulfSafe

    Agents. Risk intelligence and family safety for the Gulf. Built solo, live. gulf-safe.com

    A live risk map of the Gulf, with situation reports and SafeConnect, a way for families to check in with each other. It reads news and feeds from 12 countries every 15 minutes and shows a risk level for each country on a 3D globe.

  5. The Novessa website
    Novessa

    Agents. Founder, August 2026 to now. novessa.tech

    Builds AI agents and voice agents for businesses. The research side is about keeping a person's voice, memories and way of thinking after they pass away within reach of the family who loved them.

  6. AI interviewer

    Voice AI. In build now

    Voice and video interviews built around the role and the candidate's CV, with proctoring and a written evaluation for the hiring team.

Also built: Credit memo agent, Credit-risk signals from SEC filings, Crypto trading bot, Personality from speech, On-device voice assistant, Agentic HR, hiring workflow system, RAG chunking strategies, Muse Meet, NextRole, explainable resume matching, TeslaTrend AI.

Experience

I lead a small AI team at Encegen AI Labs, I'm the founder of Novessa, and I document my builds on YouTube.

Founder, NovessaAug 2026 to now

An AI research company working on personality modelling and voice cloning to recreate deceased individuals, plus agentic and voice AI.

AI/ML Engineer and Team Lead, Encegen AI LabsFeb 2026 to now

Lead the AI team across several client products at once: set sprint goals, own architecture and code review, report progress to stakeholders, and have run 10+ technical interviews that fed into hiring decisions. Lead the team building a multi-tenant real-time voice AI platform and own its voice pipeline and telephony layer. Tech lead on AI-assisted title due diligence for secured lending, where I own the LLM pipeline. Own the core AI pipeline on a document intelligence platform processing 10,000+ scanned legal and property documents, replacing OCR with multimodal LLM extraction, confidence-based validation, automated risk flagging and reviewer sign-off. Built the evaluation and guardrail layer across client LLM features: input, output and retrieval guardrails, regression suites, hallucination testing, and tracing through LangSmith and OpenTelemetry. Redesigned CV screening from 20 to 100 resumes per batch, cutting processing from 200 to 30 minutes (85% less).

AI/ML Engineer Intern, Encegen AI LabsAug 2025 to Feb 2026

Built LLM pipelines, prompt workflows and multi-agent orchestration, with live AWS deployments across client environments. Promoted to team lead within six months.

Software Engineer, Dexter IntelligenceMar 2025 to Aug 2025

Contributed to two mobile apps: a children's educational app with 60,000 downloads and a road navigation app with 10,000.

Software Engineer Intern, Dexter IntelligenceOct 2024 to Mar 2025

Built full-stack features for a real estate platform and a resort booking site, including search and data filtering, then was promoted to a full engineering role.

Software Engineer Summer Intern, Al Qoud Enterprise, ManamaJul 2021 to Sep 2021

Built features for a restaurant and food delivery app in a small team, my first commercial work in a shared codebase.

Artificial Intelligence and Robotics, University of HertfordshireSep 2023 to Feb 2025

Award-winning dissertation on speech recognition.

Computer Engineering, University of BahrainSep 2018 to Jan 2023

Capstone: MBTI Speech Recognition, real-time personality classification from speech. First prize and a national award nomination.

Download my CV (PDF)

A handwritten manuscript page

Verify

People stay in the loop where a mistake is expensive

Every handwritten deed goes to a human reviewer, however confident the model is. On a legal document, slower beats confidently wrong.

Telephone switchboard operators at work in the 1940s

Stream

Latency is part of the product

On a phone call a second of silence feels broken, so every stage streams instead of waiting for the one before it to finish.

A valve module from a 1960s punched card computer

Test

Tests before trust

The lending pipeline has 164 automated tests, and they run on every change.

The underwriting floor inside Lloyd's of London

Guard

Public means abuse-proof

This site rate-limits its agent, asks for a clear yes before it books anything, and stops it repeating its own instructions.

Plug me into your AI

This site runs a public MCP server. Add it to Claude, Cursor or any MCP client, then ask your own assistant whether I fit your role. It reads the same verified notes as the agent above, and it can book a call too.

https://vishitjiwane.com/api/mcp

See all 10 tools and setup for Claude and Cursor

Set it up

Let's talk

Vishit Jiwane
EmailLinkedInGitHubYouTubeCV (PDF)

Open to AI engineering roles in London, ideally in financial services or insurance. Needs Skilled Worker sponsorship. Qualifies at the new-entrant rate, which lowers the salary threshold the role has to meet. My agent checks my calendar and sends you a calendar invite.