AI Engineer - India
Explicitly requires vibe coding skills—uses tools like Replit, Cursor, Google AI Studio, and GitHub Copilot to generate and integrate code into products.
About the Role
Pulsora is hiring an experienced AI Engineer in India to design, build, and deploy production-grade LLM and generative-AI systems. The role focuses on LLM integration, agentic workflows, RAG pipelines, fine-tuning, and end-to-end full-stack implementation while collaborating with US-based teams.
Job Description
Role
Pulsora seeks an AI/ML Developer specialized in Large Language Models (LLMs) and generative AI to develop, integrate, and optimize production-grade LLM applications. The engineer will own end-to-end implementation from frontend to backend and enable sophisticated agentic workflows and RAG-based systems.
Key Responsibilities
- Design, develop, and deploy production-grade applications leveraging various LLMs and context-optimization techniques.
- Architect and implement multi-step, multi-agent workflows using frameworks like LangChain and LangGraph.
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines, including embeddings, vector databases, vector search, and reranking mechanisms.
- Lead LLM fine-tuning efforts (e.g., LoRA, QLoRA) and implement efficiency strategies.
- Develop and refine advanced prompt engineering techniques to improve model performance, consistency, and safety.
- Use AI-assisted coding tools (e.g., GitHub Copilot, Replit, Cursor, Google AI Studio) for code generation, testing, refactoring, and integration.
- Expose AI/LLM functionality across language boundaries (Python-based AI logic integrated via Java services) and leverage Java multi-threading as needed.
- Implement frontend UIs and integrate them with backend services (REST APIs) when required.
- Collaborate closely with product managers, QA, and distributed engineering teams; be willing to partly work US hours.
Requirements
- Undergraduate degree in Computer Science or a similar engineering field (advanced degree a plus).
- 5+ years of professional software development experience, with at least 2 years focused on AI/ML and LLMs.
- Strong proficiency in Python and data science libraries such as Pandas, NumPy, and Scikit-learn.
- Hands-on experience integrating major LLM APIs (public and private/local) such as Gemini, OpenAI, Anthropic, Llama, Ollama, etc.
- At least 1 year of practical experience with LangChain and LangGraph for building complex LLM applications and agentic workflows.
- Solid understanding and implementation experience with RAG architectures, embeddings, vector DBs/vector search, and reranking.
- Experience using AI-assisted coding tools (e.g., GitHub Copilot) to accelerate development, code generation, and testing.
Nice-to-haves
- Experience creating UIs with React and integrating via REST APIs.
- Hands-on Java experience, especially integrating Java modules with Python and leveraging multi-threading.
- Domain knowledge in ESG and sustainability.
Location & Logistics
- Role listed for India (title: “AI Engineer - India”).
- Collaboration with US teams is required; candidate must be willing to partially work US working hours.
- Company notes a hybrid-friendly work environment with in-office expectations (2–3 days/week) for staff in New York, San Francisco Bay Area, and Munich; local expectations for India are not explicitly stated.
Compensation & Perks
- Compensation includes salary, equity, and benefits (details not specified in the posting).
Work Style & Culture
- High ownership and autonomy, strong collaboration across small teams, emphasis on shipping production-ready products, and operating in a fast-paced, execution-focused environment.