AI Product Engineer
About the Role
NuSummit is seeking an AI Product Engineer to lead GenAI product development initiatives across our portfolio of enterprise clients. Key Responsibilities: • Lead R&D for Generative AI products including LLM integration and prompt engineering • Design and implement RAG (Retrieval-Augmented Generation) pipelines for enterprise search and Q&A systems • Build and fine-tune AI models using PyTorch and Hugging Face • Collaborate with product and engineering teams to take AI features from concept to production • Evaluate and integrate leading LLM APIs (OpenAI GPT, Anthropic Claude, etc.) • Optimize inference performance and manage AI cost-efficiency • Document architectures, conduct experiments, and publish learnings About NuSummit: NuSummit is at the forefront of AI-driven enterprise transformation, working with clients across banking, healthcare, retail, and technology sectors.
Requirements
Required Skills & Experience: • 3+ years of Python development with a focus on AI/ML • Hands-on experience with LLMs — GPT-4, Claude, or equivalent models • Strong understanding of RAG architectures and vector databases (Pinecone, Weaviate, FAISS) • Experience with PyTorch and ML model deployment • Prompt engineering skills — both zero-shot and few-shot techniques • Familiarity with LangChain, LlamaIndex, or similar frameworks • Experience deploying AI applications in cloud environments (AWS/Azure/GCP)
Required Skills
- Python
- LLMs
- GPT
- Claude
- RAG
- PyTorch
- Prompt Engineering
Apply Now →
Or browse all open positions at TalentNest HR