Explicitly requires vibe coding skills—uses Replit, Cursor, Google AI Studio, and GitHub Copilot to generate and assemble frontend and backend apps without hand-writing all code.
About the Role
Senior AI/LLM Engineer to design, build, and deploy production-grade LLM and generative AI systems, including agentic workflows and RAG pipelines, with strong Python expertise and experience integrating AI services into full-stack applications. The role focuses on LLM integration, fine-tuning, prompt engineering, and using AI-assisted coding tools, and requires collaboration across product, QA, and US-based teams.
Job Description
Role
We are hiring an AI/LLM Engineer to develop, integrate, and optimize production-grade LLM and generative AI systems. The role emphasizes building agentic workflows, Retrieval-Augmented Generation (RAG) pipelines, LLM fine-tuning, prompt engineering, and delivering end-to-end solutions that integrate frontend and backend components.
Key Responsibilities
- Design, develop, and deploy production applications leveraging various LLMs with context optimization.
- Architect and implement multi-step, multi-agent workflows using frameworks such as LangChain and LangGraph.
- Build and optimize RAG pipelines, including embeddings, vector databases, vector search, and reranking mechanisms.
- Lead LLM fine-tuning efforts (e.g., LoRA, QLoRA) and apply efficiency and context management techniques.
- Develop and refine advanced prompt engineering techniques to improve model performance, consistency, and safety.
- Use AI-assisted code generation tools (e.g., Replit, Cursor, Google AI Studio, GitHub Copilot) to generate, test, and integrate application components.
- Implement end-to-end full-stack features (frontend to backend), integrating UIs (React) with backend services via REST APIs where required.
- Expose Python-based AI/LLM functionality via Java services and leverage multi-threading when applicable.
- Maintain code quality by leveraging AI-powered development tools for generation, refactoring, and optimization.
- Collaborate closely with team leads, managers, QA, and product teams; be willing to partially work US hours.
Requirements
- 6+ years professional software development experience, with at least 2 years focused on AI/ML and LLM work.
- Strong proficiency in Python and related data libraries (Pandas, NumPy, Scikit-learn).
- Practical experience integrating public and private/local LLMs (examples cited: Gemini, OpenAI, Anthropic, Llama, Ollama).
- 1+ year of hands-on experience with agentic/agent frameworks such as LangChain and LangGraph.
- Demonstrated experience building RAG architectures, embeddings, vector DBs, vector search, and reranking.
- Experience with LLM optimization and fine-tuning techniques (LoRA, QLoRA) and context management.
- Experience creating UIs with React and integrating them with backend services is a strong plus.
- Java experience and integrating Java modules with Python modules is a plus.
- Experience using AI copilot/generative coding tools to accelerate development and testing.
- Undergraduate degree in Computer Science or similar; advanced degree is a plus.
Preferred / Nice-to-have
- Full-stack development experience across frontend and backend.
- Domain knowledge in ESG and sustainability (industry knowledge desirable).
- Experience with multi-threaded Java services and Python-Java interoperability.
Benefits and Work Arrangement
- Compensation structure includes salary, equity, and benefits.
- Hybrid-friendly work environment: in office 2–3 times per week for candidates in New York, San Francisco Bay Area, and Munich.
- Opportunity to work with leading-edge technologies on sustainability/ESG-focused products.
Location & Hours
- Hybrid role with expectations to overlap with US working hours for collaboration. Offices/teams referenced in New York, San Francisco Bay Area, and Munich.