Overview
Skills
Job Details
Job Role: Senior AI / ML Engineer
Location: Austin, TX ( 100% onsite role)
Duration: Long Term Contract
Job Description:
Key technical components include:
* FastAPI / Litestar microservices with async/await
* Multi-provider LLM orchestration (Azure-OpenAI, Google Gemini, Vertex AI)
* Vector search and embedding pipelines
* Cloud integrations (Azure AI, Google Cloud)
* Observability with OpenTelemetry and distributed tracing
* Type-safe Python with comprehensive testing
What You'll Do
Design and implement backend services for AI/ML workflows.
Develop and optimize LLM integration layers with support for tool calling and streaming.
Build and scale vector search capabilities and embedding pipelines.
Implement robust error handling, retries, and caching strategies.
Enhance observability with metrics, logging, and distributed tracing.
Maintain high code quality through code reviews, testing, and CI/CD.
Collaborate on system architecture and technical decision-making
Technical Requirements
* 6+ years of Python development with async/await experience
* Strong background in API development (FastAPI, Django, or similar)
* Experience with LLM integration and prompt engineering.
* Familiarity with vector databases and embedding models.
* Cloud platform experience (Azure, Google Cloud Platform, or AWS).
* Strong testing background (pytest, unit/integration testing).