Senior AI Engineer Backend
Summary
Builds and deploys production-grade GenAI systems: RAG pipelines, LLM integrations, and backend services in Python (FastAPI/Flask) on AWS.
Senior AI Engineer
Department: Backend
Employment Type: Full Time
Location: Dallas, Texas, USA, Remote
Key Responsibilities
- Design and build RAG systems, embeddings, vector search, chunking, and evaluation pipelines.
- Build and maintain multi-agent orchestration workflows (LangGraph, AutoGen, CrewAI, or similar).
- Develop backend services and APIs (Python — Flask/FastAPI) that expose AI workflows to production systems.
- Deploy and scale AI workloads in cloud-native environments, using serverless or containerized patterns.
- Implement LLMOps practices: prompt versioning, cost tracking, monitoring, and evaluation.
- Write clean, tested code, and use AI-assisted tools (Copilot, Cursor, Claude Code) to move faster without cutting corners.
- Work with data and platform engineers to ship GenAI features quickly, from prototype to production.
Skills, Knowledge and Expertise
Must-Have Skills
- 5+ years of backend experience, with strong Python coding skills.
- Proven experience shipping RAG systems (vector DBs, embeddings, chunking).
- Familiarity with orchestration frameworks (LangGraph, LangChain, AutoGen, or similar).
- Experience with APIs, microservices, and cloud-native development (AWS preferred).
- Familiarity with distributed systems concepts (async, message queues, caching).
Nice-to-Have
- Experience with unstructured data (PDFs, tables, images).
Soft Skills
- Builder mindset: thrives on writing, debugging, and improving production code.
- Collaborative, humble, and open to feedback.
- Strong communicator who explains design decisions clearly.