AI & Data Intern – Retrieval Systems, Automation & Sustainability

Help Build the AI Engine for a Greener Future

Position :

AI & Data Intern – Retrieval Systems, Automation & Sustainability

Location : On-site (Delhi NCR)

Duration :

Minimum 3 months (extendable to 6 months)

Stipend Provided | Certificate | Pre-Placement Offer Opportunity

About Novasensa

Novasensa is a deep-tech sustainability company developing next-generation technologies for lithium-ion battery and e-waste recycling. Our systems recover valuable and critical metals from used electronics—powering the transition to clean energy and a circular economy.

We’re now building

NovaGenesis 1.0 , an AI platform that understands scientific and experimental data to deliver context-driven insights for our R&D and process automation workflows.

We’re looking for people who

love hard technical challenges ,

think independently , and want to help build a world-class AI product with real-world impact. If you perform strongly, this role can convert into a full-time position.

What You’ll Be Building

NovaGenesis aims to interpret and reason over complex experimental data. The system combines document understanding, semantic retrieval, and intelligent response generation to assist scientists and engineers in decision-making.

You’ll help solve real problems such as :

Improving

context retrieval

from structured scientific and experimental data

Enhancing

semantic accuracy

and

context alignment

between retrieved content and model output

Building scalable document-parsing and data-automation workflows

Developing

metadata-aware retrieval logic

for multi-format lab files

Your work will directly influence how AI supports sustainable materials recovery and laboratory automation.

Responsibilities

AI & Backend Development

Implement and optimize retrieval and semantic-search pipelines

Design and test chunking, indexing, and data-processing logic for mixed document types

Improve context precision and minimize hallucination through better alignment techniques

Automation & Data Engineering

Write Python scripts to parse and organize structured lab data

Automate data tracking, visualization, and reporting workflows

Build lightweight interfaces (e.g., Streamlit) for experiment monitoring

System Improvement & Testing

Evaluate performance of retrieval pipelines and propose algorithmic enhancements

Work closely with domain experts to align AI responses with real scientific data

Who We’re Looking For

We want

builders , not just learners—people who can debug, reason, and deliver.

Must-Have

Solid Python programming and debugging skills

Understanding of data structures, OOP, and file handling

Experience or coursework in AI, ML, or data-driven systems

Curiosity to design retrieval-augmented or knowledge-based applications

Good to Have

Experience with vector databases or semantic search frameworks

Exposure to document-parsing or automation libraries

Knowledge of prompt-engineering and context optimization

Interest in sustainability, recycling, or applied AI in scientific domains

Education

B.Tech / M.Tech / B.E. in Computer Science, AI / ML

B.Sc / M.Sc in Computer Science, AI / ML,

Why Join Us

Build a real AI system from first principles—no toy projects

Work directly with founders and researchers driving India’s clean-tech innovation

Every contribution you make will have measurable environmental impact

Strong performers will be considered for

long-term or full-time roles

Learn. Build. Impact.

Join us to create the AI backbone of sustainable innovation.