AI/LLM Engineer
Pulsora
Location
India
Employment Type
Full time
Location Type
Hybrid
Department
Engineering
Founded in 2021, Pulsora the “Enterprise Sustainability Platform”, is a well-funded Silicon Valley software startup. It is dedicated to empowering purpose-driven enterprises to manage and improve their environmental, social, and governance (ESG) and overall sustainability footprint with an integrated, comprehensive, flexible, and innovative technology platform built for compliance, tracking, and insight. We are well funded, have amazing customers across industries and geographies, established strategic partnerships with leading ERP and consulting firms, and are growing fast!
About the role
We are seeking a highly skilled and experienced AI/ML Developer to join our team. The ideal candidate will be a specialist in the rapidly evolving field of Large Language Models (LLMs) and generative AI, with a strong background in developing, integrating, and optimizing complex agentic and RAG-based systems. This role requires deep expertise in modern AI frameworks, prompt engineering, context optimization, and practical LLM fine-tuning techniques. A strong proficiency in Python is essential. A full-stack development experience, particularly with Reac and experience integrating Java modules with Python modules, are significant advantages..
Key Responsibilities – What you will be doing
LLM Integration & Development: Design, develop, and deploy production-grade applications leveraging various LLMs, context optimization, etc.
Agentic Workflows: Architect and implement sophisticated, multi-step and multi-agent workflows using frameworks like LangChain and LangGraph.
Retrieval Augmented Generation (RAG): Build and optimize RAG pipelines, including implementing and managing embeddings, vector databases, and advanced rerankers to enhance response quality and relevance.
Vibe Coding: Use code generation applications (e.g. Replit, Cursor, Google AI Studio, Git Hub Copilot in Agent mode, etc.) to create full applications (including frontend and backend), generate tests, perform testing and integrate them in the core product without writing any code.
LLM Fine Tuning: Lead efforts in LLM fine-tuning (e.g., LoRA, QLoRA) for specific domain knowledge and tasks, and implement strategies for and efficiency.
Prompt Engineering: Develop and refine advanced prompt engineering techniques to maximize model performance, consistency, and safety.
Full-Stack Development (huge plus): Do end-to-end implementation from frontend to the backend. Highly desired.
Java (Plus): Expose AI/LLM functionality written in Python using Java services, leverage multi-threading capabilities in Java to augment AI/LLM functionality developed in Pyhton
Code Quality & Productivity: Utilize AI-powered development tools (e.g., GitHub Copilot, etc.) to efficiently generate, refactor, and optimize high-quality code.
Collaboration: Work closely with team leads managers, QA, product managers and team in the US (this will require the willingness to partially work US working hours)
Qualifications – What you will need for this position
Experience: 6+ years of professional experience in software development, with a minimum of 2 years focused on AI/ML development, particularly with LLMs.
Programming: Strong proficiency in Python and its relevant data science libraries (e.g., Pandas, NumPy, Scikit-learn).
LLM Expertise: Proven experience integrating and working with major LLM APIs - both public LLms and private/local LLMs, e.g., Gemini, OpenAI, Anthropic, Llama, Ollama, etc.
Agentic Frameworks: 1+ year of deep practical experience with LangChain and LangGraph for building complex LLM applications and agentic workflows using autonomous agents, tools, memory management, parallelization, etc.
RAG: Solid understanding and implementation experience with RAG architectures, vector DBs, vector search, embeddings, and reranking mechanisms.
Optimization: Hands-on experience with techniques for LLM efficiency, fine-tuning, and context management.
Full-Stack/frontend experience(Plus): Experience creating UI using React and integrating the UI with the backend using REST APIs is a big plus.
Java (Plus): Hands-on experience with Java, especially integrating Java modules with Python modules is a big plus.
AI-Copilot: Experience leveraging AI Copilot or similar generative AI coding tools for accelerated development, code generation, refactoring, and optimization, vibe coding to create integrated backend and frontend applications.
Must have undergraduate degree in Computer Science or similar Engineering field, advanced degree a plus
Benefits – What’s in it for you
Work for the industry leader and innovative company
Work with multiple leading-edge technologies
You get to work on a solution that helps the planet and helps us all
Why work at Pulsora?
We believe that progress happens by bringing together people from all walks of life who have the drive and the influence to improve our world now and for the next generations!
Ideally have industry and market knowledge of ESG and sustainability
The company will pay with salary, equity, and benefits
You’ll get to work on problems that are hard and important
You get to work on a solution that helps the planet and helps us all
You’ll be joining an extraordinary team at the beginning of an extraordinary journey
Hybrid-friendly work environment, in office 2-3 times per week (for those in New York, San Francisco Bay Area, and Munich)
Pulsora Core Values
Compassionate candor
Transparency
Embrace diversity and cultivate belonging
Make a positive impact
Delight customers
Join us and become a driver for positive change!