GenAI Multimodal Scientist: Prompting & Video Analytics

LTM; Edison (NJ); On-site; USD 120,000 - 190,000; Full time

Benefits offered by this job

Comprehensive Medical Plan

401(k) Plan with Company match

Paid Holidays

Job summary

LTIMindtree is seeking Applied Scientists at Lead/IC levels to design and optimize GenAI-driven multimodal pipelines for detecting contextual moments in live video streams. You will work on prompt strategies, multimodal inference, and structured outputs to integrate GenAI results into downstream systems.

The role emphasizes hands-on experience with AWS Bedrock, Lambda, S3, and Kinesis, plus collaboration with QA for production rollout and continuous improvement.

Qualifications

• Prompt engineering for foundation models like Claude Nova, etc.
• Multimodal AI systems including vision and NLP.
• Strong Python programming and data pipeline skills.
• Hands-on experience with LLM inference and optimisation.

Responsibilities

• Design and optimise prompt engineering strategies for foundation models.
• Build pipelines for multimodal inference (video transcript, audio).
• Detect and classify contextual moments and custom events.
• Develop reusable frameworks and moment detection templates.

Skills

Prompt engineering

Multimodal AI

Python

Video analytics

LLM inference

Tools

AWS Bedrock

Lambda

S3

Kinesis

Job description

LTIMindtree is seeking Applied Scientists at Lead/IC levels to design and optimize GenAI-driven multimodal pipelines for detecting contextual moments in live video streams. You will work on prompt strategies, multimodal inference, and structured outputs to integrate GenAI results into downstream systems.

The role emphasizes hands-on experience with AWS Bedrock, Lambda, S3, and Kinesis, plus collaboration with QA for production rollout and continuous improvement.