Nilay Baranwal
  • WorkSection
  • WritingSection
  • LabSection
  • Open sourceSection
  • GallerySection
  • AboutSection
  • ResumeSection
  • ContactSection
  • Hive MindProject
  • Pre-trade dashboardProject
  • Social LineProject
  • PartymakerProject
  • Orvio.aiProject
  • Agentic property managementProject
  • AI agents now outwork humans at Anthropic. Junior engineers are feeling it first.Article
  • Anthropic replaced git. Here's why you probably shouldn't.Article
  • Recruiters can now interview your AI twin. Here's what it actually checks.Article
  • Everyone's building a Jev rival. The independent numbers tell a different story.Article
  • Jev vs OpenAI Decisions API: which decision model should your agent use?Article
  • Top 10 Jev use cases in agentic appsArticle
  • Jev vs Laya: decision modelsArticle
  • LLMs or Jev: where each one actually fitsArticle
  • Everyone's talking about Jev. Here's a closer look at what the data shows.Article
  • Live agent with an approval gateLab
  • AI engineer interview, beginner pathLab
  • Behavioural interview coachLab
  • Interview drill, experiencedLab
  • AI adoption plannerLab
  • Discovery call simulatorLab
  • Scope a vague problemLab
  • MCP analyzerLab
  • MCP inspectorLab
  • Tool gate playgroundLab
  • Prompt-injection spotterLab
  • RAG chunking visualizerLab
  • Eval benchLab
  • Agent trace debuggerLab
  • Prompt caching simulatorLab
  • Context window budgetLab
  • textagentOpen source
  • Help EngineerOpen source
  • Email nilaybaranwal@gmail.comContact
  • Connect your agent to my MCP serverLab
  • LinkedInContact
  • GitHubContact

About

Forward Deployed Engineer and AI Engineer, Prague, Czech Republic

After Keith Haring, Subway Drawings, 1980–85. Chalk on black paper, drawn on empty ad panels.

Seven years of turning vague problems into working systems and keeping them running in production. At Barclays I sat with traders to build the pre-trade dashboard they use daily, and now I'm building Hive Mind, the MCP server that connects AI agents to the bank's pre-trade systems.

On the side I've built four AI products from zero and deployed each into a real operating environment: Prague nightclubs on event night, marketing teams inside their own analytics stacks, and short-term rentals run by agents.

Experience

Read the full resume

  1. May 2021 to now

    Barclays, Senior Full Stack Software Engineer

    Embedded with the Markets pre-trade desk. Primary technical contact for traders and desk heads: demos, discovery, requirements and release plans.

  2. May 2019 to Feb 2022

    TEDxKanke, Lead Full Stack Developer (remote)

    Sole technical partner to a non-technical organising team. Scoped and launched the event platform; registrations grew 250%.

  3. May to Aug 2018

    Nationale-Nederlanden, Junior Software Engineer

    Eight PeopleCode modules for an HR system serving 3,000+ employees, with requirements gathered from regional HR teams. Reports 40% faster.

  4. Jan to Apr 2018

    Commerzbank, Junior Software Engineer

    Spring Boot work on banking applications serving 100,000+ customers daily.

  5. 2016 to 2022

    Czech Technical University in Prague, B.Tech, Software Engineering

Toolbox

Agents
Agent harnesses and loops, multi-agent orchestration, MCP server and tool design, Claude Agent SDK, OpenAI Agents SDK, LangGraph, Vercel AI SDK, human-in-the-loop guardrails
Memory and retrieval
Agent memory, context engineering and compaction, RAG, embeddings, pgvector, Pinecone, hybrid search and reranking
Evals and LLMOps
Golden datasets, LLM-as-judge, regression suites, Langfuse, LangSmith, prompt caching, model routing
Product engineering
TypeScript, React, Next.js, Node.js, Python, Java Spring, GraphQL, PostgreSQL, Redis, Firebase
Cloud
AWS, Google Cloud, Azure, Vercel, Docker, Kubernetes, CI/CD, observability
Payments and compliance
Stripe, payouts, PSD2 surcharging, VAT treatment, GDPR (LIA, DPIA, Art. 14)