AI/LLM Engineer

2w2 weeks ago

pulsESG

IN · Full-time · INR 3,000,000 – INR 6,000,000

About this role

Founded in 2021, Pulsora the “Enterprise Sustainability Platform” is a well-funded Silicon Valley software startup. It empowers purpose-driven enterprises to manage ESG sustainability with an integrated, comprehensive technology platform. We seek a highly skilled AI/ML specialist in Large Language Models and generative AI.

The role focuses on developing, integrating, and optimizing agentic and RAG-based systems using modern AI frameworks. Key work includes LLM integration, multi-agent workflows with LangChain and LangGraph, and advanced RAG pipelines with embeddings and vector databases. Proficiency in Python is essential for production-grade deployments.

Expect hands-on vibe coding with tools like Cursor and GitHub Copilot to build full applications without writing code. Fine-tune LLMs via LoRA and QLoRA, refine prompt engineering, and leverage AI tools for code quality. Full-stack experience with React and Java integration are significant advantages.

Collaborate closely with US-based team leads, QA, and product managers, requiring partial US working hours. Join a fast-growing team with amazing customers across industries, strategic ERP partnerships, and innovative sustainability tech. Drive impact in a dynamic, purpose-driven environment.

Requirements

6+ years of professional experience in software development, with minimum 2 years focused on AI/ML particularly LLMs
Strong proficiency in Python and relevant data science libraries like Pandas, NumPy, Scikit-learn
Proven experience integrating and working with major LLM APIs
Deep expertise in modern AI frameworks, prompt engineering, context optimization, and LLM fine-tuning techniques
Experience developing agentic workflows and RAG-based systems
Full-stack development experience particularly with React
Experience integrating Java modules with Python modules

Responsibilities

Design, develop, and deploy production-grade applications leveraging various LLMs and context optimization
Architect and implement sophisticated multi-step and multi-agent workflows using frameworks like LangChain and LangGraph
Build and optimize RAG pipelines, including embeddings, vector databases, and advanced rerankers
Use code generation applications like Replit, Cursor, GitHub Copilot to create full applications without writing any code
Lead LLM fine-tuning efforts with LoRA, QLoRA for domain knowledge and efficiency
Develop and refine advanced prompt engineering techniques for model performance and safety
Utilize AI-powered tools to generate, refactor, and optimize high-quality code
Work closely with US team leads, QA, product managers requiring partial US working hours