# Deepankan Srivastava

Deepankan Srivastava is a remote worker on Himalayas, Software Engineer at Capital Numbers Infotech, based in India.

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

```text
AI Engineer specializing in LLMs, RAG, and scalable production MLOps solutions.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | India |
| Authorized to work in | India |
| Job categories | AI Engineer, Machine Learning Engineer, MLOps Engineer, Data Scientist, Software Engineer, NLP Engineer, Research Engineer, AI Product Manager, DevOps Engineer, AI ML Engineer, AI Solutions Engineer, Senior AI Engineer |
| Skills | RAG, Large Language Models, Prompt Engineering, Embeddings, Lang Chain, LangGraph, Crew AI, AutoGen, Hugging Face, Transformers, PyTorch, Pytorch Lightning, TensorFlow, Keras, Deep Learning, Natural Language Processing, Computer Vision, Python, SQL, Pandas, NumPy, ChromaDB, Pinecone, Faiss, LlamaIndex, PostgreSQL, MySQL, BigQuery, Docker, Kubernetes, CI CD, fastAPI, Flask, REST APIs, gRPC, Twilio, ElevenLabs, Streamlit, VLLM, Apache Spark, Tableau, scikit learn, XGBoost, LightGBM, CatBoost, MongoDB, GitHub, Chi, Multi Modal RAG |

## What I'm looking for

```text
I seek roles building production LLM and RAG systems with strong MLOps practices, collaborative teams, and opportunities to scale secure AI products.
```

## About

```text
I am an AI Engineer with 2+ years of hands-on experience building LLM-driven, agentic, and multimodal Retrieval-Augmented Generation systems for enterprise customers. I design and deploy scalable, secure AI platforms—ranging from Perplexity-style private RAG engines to voice-enabled Twilio agents—while focusing on performance, reliability, and cost-effective model routing.

My work includes architecting multimodal RAG with LangGraph, integrating Llama-family models with vector stores like Pinecone and Chroma, and productionizing pipelines on AWS and GCP. I have delivered concrete outcomes such as reducing manual scheduling by 40%, cutting query resolution time by 30%, and boosting legal-document review efficiency by 50%.

I combine deep technical skills (LangChain, embeddings, fine-tuning, PyTorch/TensorFlow) with strong MLOps and cloud deployment experience to move prototypes into production. I enjoy solving domain-specific retrieval problems, building robust APIs, and optimizing systems for large-scale, secure access to organizational knowledge.
```

## Experience

### Software Engineer (current)

Capital Numbers Infotech. Jan 2024 - Present

```text
Designed and implemented an enterprise-grade Perplexity-style AI platform and multimodal RAG systems, delivered voice-enabled phone agents that reduced manual scheduling by 40%, and built legal and medical AI tools that improved document analysis efficiency by up to 50%.
```

Skills: LLMs, LangGraph, Twilio, ElevenLabs, Pinecone, VLLM, Multi-Modal-RAG, LLM

### Associate Software Developer

Tmotions Global Pvt. Ltd. Jan 2023 - Jan 2024

```text
Integrated Llama2 with ChromaDB and deployed scalable AWS solutions, built high-performance QA systems that reduced query resolution time by 30%, and designed reusable APIs and data ingestion frameworks that cut manual data wrangling by 25%.
```

Skills: EC2, LLaMA-2, ChromaDB, API-Design, SQL, MongoDB

## Education

### Scaler

Professional Certificate, Data Science & Machine Learning. 2022 - Present

Activities and societies: Won Scalerʼs Statistics Master Award (2022)

```text
Enrolled in an intensive Data Science & Machine Learning program focused on practical ML, deep learning, and engineering for production-grade AI systems.
```

### Lovely Professional University

Bachelor of Computer Applications (Hons.), Computer Applications. 2016 - 2019. Grade: 9.43 CGPA

```text
Completed a Bachelor of Computer Applications (Hons.) with strong academic performance and received Honor Roll for Academic Excellence in 2018.
```

## Tech stack

- Apache Spark
- GitHub
- Kubernetes
- NumPy
- Pandas
- MySQL
- PostgreSQL
- MongoDB
- Gmail
- TensorFlow
- PyTorch
- scikit-learn
- Keras
- Streamlit
- FastAPI
- gRPC
- Twilio
- Google BigQuery
- SQL
- XGBoost
- Hugging Face
- LightGBM
- CatBoost
- LangChain
- LlamaIndex
- ChromaDB
- AutoGen
- Pinecone
- CrewAI
- ElevenLabs
- vLLM
- Evidence
- Chi

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

## People also viewed

- [Akhil Salla](https://himalayas.app/@akhilsalla): Software Engineer, Nexquare
- [Rohit Kumar](https://himalayas.app/@rohitkumar21): AI/ML Engineer, Frisson Devhub
- [Aditya Ware](https://himalayas.app/@adityaware): AI Engineer, Freelance
- [Yash Kumar](https://himalayas.app/@yashkumar7): Founding AI Engineer, GeniOS
- [Kshitij Kumrawat](https://himalayas.app/@kshitijkumrawat): AI/ML Engineer Intern, DBlytics
- [Sidh Su](https://himalayas.app/@Surya_M_R): Associate Data Scientist, Kovai.co
- [Asmit Verma](https://himalayas.app/@asmitverma): Trainee Engineer AI/ML, Coforge
- [Avinash Lodhi](https://himalayas.app/@avinashlodhi): AI/ML Engineer, Hestabit Technology
- [Srinivasan User](https://himalayas.app/@rsrinivasan): Senior Software Engineer – AI Systems, XYMA Analytics
- [Ankit Singh](https://himalayas.app/@ankitsingh39): Autonomous Research Agent, Personal Project
