# Jaikishan User

Jaikishan User is a remote worker on Himalayas, AI Engineer - Agentic Systems at L&T Energy & Hydrocarbon, based in India.

Source: https://himalayas.app/@jaikishan2k

```text
Agentic AI engineer building multi-agent LLM systems for production workflows.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 1500k-1800k INR |
| Job categories | Artificial Intelligence Developer, AI Developer, Generative AI Engineer, LLM Engineer |
| Skills | Agentic AI, Multi Agent Systems, LangGraph, Lang Chain, Custom MCP Tools, MCP Servers, Supervisor Worker Patterns, Tool Use, Agent Evaluation, RAG, Structured Outputs, Prompt Engineering, LLM Observability, ChromaDB, Pinecone, Faiss, Crew AI, Agno, Google ADK, LlamaIndex, AutoGen, Qwen 3.5, YOLO, Mediapipe, PyTorch, LoRAs, Zero Shot Classification, Python, fastAPI, Node, React, Next.js, Docker, Azure OpenAI, Prometheus, Grafana, Kubernetes, Model Serving, Azure, AWS, Airflow, Apache Spark, Unreal Engine, Knowledge Graphs, NodeJS, SSO, GitHub, SQL, Qwen |
| Portfolio | https://github.com/imjaikishan |
| LinkedIn | https://https://www.linkedin.com/in/jaikishan2k/ |

## What I'm looking for

```text
I’m looking to build and ship agentic LLM systems end-to-end—multi-agent orchestration, RAG, evaluation, and observability—so production workflows become faster, safer, and measurable.
```

## About

```text
I build production AI systems at L&T, focusing on agentic orchestration, RAG pipelines, and industrial computer vision. In my current role, I lead architecture, evaluation, and end-to-end delivery in Python, turning messy workflows into reliable systems.

With a 4-agent supervisor-worker setup in LangGraph, I cut material certificate verification time from 80–90s to 20–25s and automated cross-plant certificate workflows across 6 sites. I also improved data reliability by tying supplier certificates to SAP master data through a Knowledge Graph.

I make these systems safer and easier to trust by putting observability in place—structured logging, tracing, and agentic evaluation using precision and faithfulness benchmarks against SAP ground truth. I’ve also addressed agentic security risks using Azure AD SSO and RBAC.

Beyond agents, I delivered a production RAG system for 1,000+ learners using semantic chunking, ChromaDB, and a Knowledge Graph for PDF/CSV/SQL queries. Earlier, I co-designed a synthetic data pipeline in Unreal Engine and helped drive YOLO/SSD/CNN training, while building FastAPI and Apache Spark pipelines for telemetry and document preprocessing.
```

## Experience

### AI Engineer - Agentic Systems (current)

L&T Energy & Hydrocarbon. Jan 2026 - Present

```text
Reduced material certificate verification time from 80-90 s to 20-25 s, saving ~400 engineer-hours/month, by building a 4-agent supervisor-worker system in LangGraph. Replaced 3 FTEs and cut ~₹8L/month in labour costs by automating cross-plant certificate workflows.
```

Skills: LangGraph, Agentic-Automation, Azure-AD, RBAC, LLM-Observability, Prometheus, Grafana, Mediapipe, Generative-AI, Agentic-AI, Python

### Engineer - AI Integration

[L&T Technology Services](https://himalayas.app/companies/l-t-technology-services). Apr 2024 - Dec 2025

```text
Delivered a production RAG system serving 1,000+ learners by implementing semantic chunking, ChromaDB vector store, and Knowledge Graph for PDF/CSV/SQL queries. Improved retrieval quality by 12% over baselines through systematic evaluation of embedding models.
```

Skills: RAG, ChromaDB, Knowledge-Graphs, Word2Vec, GloVe, FastText

### Associate Engineer - Design Systems & CV

[L&T Technology Services](https://himalayas.app/companies/l-t-technology-services). Dec 2022 - Mar 2024

```text
Reached 83% detection accuracy under varied lighting and weather conditions by co-designing a synthetic data pipeline in Unreal Engine producing 50,000+ auto-labelled images. Accelerated field validation cycles by building a real-time bidirectional FastAPI layer for telemetry ingestion.
```

Skills: YOLO, SSD, CNN, Unreal-Engine, Synthetic-Data, fastAPI, Apache-Spark

## Education

### Chandigarh University

Bachelor of Engineering, Computer Science and Engineering

```text
Bachelor of Engineering in Computer Science and Engineering with Information Security Specialisation.
```

## Tech stack

- Apache Spark
- Microsoft Azure
- GitHub
- Kubernetes
- PostgreSQL
- Node.js
- Next.js
- Unreal Engine
- Figma
- React
- JavaScript
- Python
- HTML5
- PyTorch
- FastAPI
- Grafana
- Prometheus
- GraphQL
- TypeScript
- sso
- Airflow
- SQL
- LangChain
- LlamaIndex
- ChromaDB
- AutoGen
- Pinecone
- CrewAI
- OpenAI API
- Agentic
- Faiss
- LangGraph
- Qwen
- MediaPipe
- Agno

To contact Jaikishan, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Pratik Karnik](https://himalayas.app/@pratikskarnik): Senior Associate Projects, Cognizant Technology Solutions
- [Shivam Gulati](https://himalayas.app/@shivamgulati): Data Scientist, Quara AI Tech Pvt Ltd
- [Sidh Su](https://himalayas.app/@Surya_M_R): Associate Data Scientist, Kovai.co
- [Purvi User](https://himalayas.app/@purviuser): AI Engineer, Reqpedia
- [Yuval Mehta](https://himalayas.app/@yuvalmehta): Generative AI Engineer, XLM Continuous Intelligence
- [Kunal User](https://himalayas.app/@kunaluser11): Computer Vision Intern, Tata Steel
- [Abrar Ahmed](https://himalayas.app/@abrarahmed2304): Associate Product Engineering, Keenai Global
- [Afham Ahmad](https://himalayas.app/@afhamahmad): Machine Vision Intern, KlarSYS Automations LLP
- [Jaydatta Bade](https://himalayas.app/@jaydattabade): AI Engineer Individual Contributor, FilersKeepers/Lawstronaut
- [Shashi kiran](https://himalayas.app/@shashikiran6): Senior Associate Consultant, Infosys Limited
