LLM Full Stack Engineer
Core
Design and develop AI/ML and Generative AI solutions, building and deploying applications leveraging Large Language Models (LLMs) and integrating them into web/mobile/backend applications.
Role type
Senior IC LLM Full Stack Engineer
Builds
End-to-end AI pipelines, LLM applications, and integrated services for clients
Domain
Generative AI, Large Language Models, NLP
Deliverable
production ML models
Required skills
Python, PyTorch/TensorFlow, LangChain/LlamaIndex, NLP concepts, REST APIs, vector databases, Git
Preferred skills
OpenAI/open-source LLM APIs, RAG architectures, model fine-tuning, AWS/GCP, Docker
Technologies
Python, PyTorch, TensorFlow, LangChain, LlamaIndex, Pinecone, FAISS, Weaviate, Docker, AWS, GCP
Responsibilities
Design and develop AI/ML and Generative AI solutions; Build and deploy applications leveraging LLMs; Develop end-to-end pipelines including data ingestion, preprocessing, model integration, and deployment; Implement prompt engineering and fine-tuning strategies; Integrate AI services into applications via APIs; Work with vector databases and embeddings for semantic search and RAG; Optimize models and pipelines for performance, latency, and cost; Monitor and improve model performance in production environments.
Seniority
Senior, hands-on IC
