Full Stack Gen AI Engineer

7 months ago

Dallas, TX, USASenior

Responsibilities

Build high-performance API services and microservices using Python and FastAPI, deployed on AWS Fargate and ECS.
Integrate generative AI and LLM APIs, including AWS Bedrock and other model providers.
Design and implement end-to-end RAG pipelines with retrievers, vector stores, document chunking, embeddings, and generators.
Develop autonomous and semi-autonomous agents using agent frameworks, with tool integration, orchestration, error handling, and context management.
Optimize latency, relevance, efficiency, grounding accuracy, and hallucination detection for production AI systems.
Use evaluation frameworks and performance metrics to iterate on and continuously improve AI applications.
Work with DevOps, CI/CD pipelines, ML pipelines, and backend infrastructure within the AWS ecosystem.

Minimum 7+ years of professional experience in software development and AI engineering.
Expertise building high-performance Python APIs and microservices with FastAPI on AWS Fargate and ECS.
Hands-on experience integrating generative AI and LLM APIs, AWS Bedrock, and other model providers.
Strong Python programming skills and a deep understanding of OpenAI API standards, JSON-based API design, and LLM orchestration.
Experience designing RAG pipelines, working with retrievers and vector stores such as Pinecone, Weaviate, or pgvector, and optimizing relevance and latency.
Practical experience developing agentic AI applications with frameworks such as LangChain, CrewAI, or Semantic Kernel.
Experience managing memory, context, tool integration, external APIs, and non-deterministic AI outputs in multi-turn interactions.
Familiarity with evaluation frameworks such as RAGAS and TruLens for assessing performance, grounding, and hallucinations.
Experience with DevOps, CI/CD pipelines, ML pipelines, and AWS infrastructure.
Experience with Bedrock Agent/Core services is preferred.

5,001-10,000 employees