LLM Full Stack Engineer
Core
Design and build scalable AI-driven applications integrating Large Language Models (LLMs) with enterprise services, balancing front-end and back-end development.
Role type
Senior Full Stack Engineer (LLM/GenAI)
Builds
Production-ready AI applications, APIs, and orchestration pipelines for enterprise clients.
Domain
Artificial Intelligence / Generative AI / Enterprise Software
Deliverable
production ML models | product features
Required skills
Large Language Models (LLMs), Generative AI, Prompt Engineering, React.js, Python, FastAPI/Django, TypeScript, Vector DBs, Azure AI services, LangGraph/AutoGen/CrewAI, CI/CD, Docker, Kubernetes, OAuth2/OIDC, JWT, RBAC, Kafka/Event Hubs, Locust/Gatling/JMeter
Preferred skills
RAG pipelines, multi-agent orchestration, document processing (OCR/PDF), feature stores, streaming architectures, cost governance for LLM workloads
Technologies
React.js, Next.js, Redux/RTK/Zustand, FastAPI, Django, Python, TypeScript, Azure AI Studio, Cognitive Search, Key Vault, Purview, Event Hubs, LangGraph, AutoGen, CrewAI, Semantic Kernel, Docker, Kubernetes, Prometheus, Grafana, App Insights, Kafka, Locust, Gatling, JMeter
Responsibilities
Lead the design and implementation of scalable AI-driven applications leveraging LLMs; Collaborate with cross-functional teams to enhance performance and scalability; Facilitate knowledge sharing and mentorship within the team; Coordinate with stakeholders to align technical solutions with business objectives; Develop and integrate APIs for AI applications; Optimize AI models and applications for performance and scalability.
Seniority
Senior, hands-on IC with team leadership responsibilities