Full Stack Gen AI Engineer
Core
Building high-performance API services and implementing complex RAG and Agentic AI architectures for Fortune 1000 clients.
Role type
Senior Full Stack Generative AI Engineer
Builds
Production-grade Gen AI applications, RAG pipelines, and autonomous agent systems
Domain
Generative AI, Cloud Infrastructure, Enterprise Analytics
Deliverable
production ML models
Required skills
Python, AWS Fargate (ECS), FastAPI, Generative AI/LLM APIs, AWS Bedrock, RAG pipeline design, Vector stores (Pinecone, Weaviate, pgvector), LangChain, CrewAI, Semantic Kernel, LLM orchestration, CI/CD pipelines, Evaluation frameworks (RAGAS, TruLens)
Preferred skills
AWS Bedrock Agent/Core services
Technologies
Python, FastAPI, AWS Fargate, AWS Bedrock, Pinecone, Weaviate, pgvector, LangChain, CrewAI, Semantic Kernel, RAGAS, TruLens
Responsibilities
Design and implement end-to-end RAG pipelines with latency optimization; Develop autonomous or semi-autonomous agents with robust error handling; Manage memory and context in multi-turn interactions; Build high-performance API/microservices deployed on AWS; Integrate LLM APIs and model providers; Iterate systems based on performance metrics and evaluation frameworks.
Seniority
Senior, hands-on IC