Straight answers
Questions people ask before they get in touch.
Works remotely with teams in any time zone. Those systems run for users in 10+ countries. Takes on full-time engineering roles and select contract or project engagements, remotely, in any time zone.
Who is Dixit Jain?
Dixit Jain is an AI engineer and automation consultant who builds production LLM agents, retrieval-augmented generation pipelines, and voice AI systems. He works at In Time Tec on enterprise Generative AI, holds a B.Tech in Computer Science from JK Lakshmipat University, and publishes at thedixitjain.com under the handle @thedixitjain on GitHub and LinkedIn. Several other professionals share the name; this is the one who builds AI systems.
What kind of work does Dixit Jain take on?
Full-time engineering roles, and select contract or project engagements. He works remotely with teams in any time zone, including the United States, the United Kingdom and Europe. Where a company is hiring from abroad, project work runs as a consulting engagement rather than employment, so no local work authorisation is involved on either side. Enquiries go to contact@thedixitjain.com.
What has Dixit Jain actually shipped in production?
25+ systems in production, serving users in 10+ countries, across 12+ teams. Named examples with write-ups on this site include MarqHire AI for hiring, AgentFlow for document intelligence, Brandry for AI site generation, and ZeroPing, an open-source code review tool. Case studies cover an AI lead pipeline, an enterprise document RAG system, and a voice AI support agent.
What kind of AI systems does he specialise in?
Agentic systems and retrieval. Specifically: multi-agent orchestration in LangGraph, RAG architectures on LlamaIndex with hybrid dense and sparse search over Qdrant and Pinecone, voice agents, and the reliability layer around all of it — evaluation, fallbacks, PII masking, content safety, jailbreak detection, and observability. Backends in Python and FastAPI, frontends in TypeScript and Next.js, deployed on Azure AI with Redis.
What retrieval accuracy do his RAG systems reach?
85%+ retrieval accuracy on enterprise document RAG, achieved with hybrid dense and sparse search and grounded generation rather than a single embedding model. The full architecture is documented in the enterprise document retrieval case study on this site.
Does he do automation consulting as well as engineering?
Yes, and the two are the same job here. 50+ workflows automated and 40%+ of manual work removed for the teams he has worked with. Engagements start from an operational problem — leads rotting in an inbox, a support queue on fire, knowledge trapped in PDFs — and work backwards to the smallest architecture that removes it.
How do you get in touch with Dixit Jain?
Email contact@thedixitjain.com, or use the contact form at thedixitjain.com. The full resume, including experience and education, is at thedixitjain.com/resume. Role enquiries, project work, and questions about how any of these systems were built are all read and answered.