Senior LLM Systems Engineer

Xora Innovation; San Diego (CA); Hybrid; USD 140,000 - 210,000; Full time

Job summary

ELEMYNT, built by Xora Innovation, seeks a senior engineer to own LLM systems behind our platform, from model internals to production services. Expect hands-on coding, evaluation, tracing, and delivering reliable capabilities across customer environments.

You will enable tool calling, multi-step planning, and robust retrieval with embeddings and RAG techniques while maintaining guardrails and cost controls.

Qualifications

• This role requires 5+ years shipping production software including LLM-powered systems.
• Strong Python and API experience; async, HTTP, streaming, testing, code review.
• Production LLM experience with prompting, context engineering, tool calling, and structured output.

Responsibilities

• Build and ship end-to-end LLM-powered capabilities for production use.
• Design agents with planning, tool usage, memory, and robust failure handling.
• Develop retrieval with embeddings, chunking, and hybrid search; improve RAG quality.

Skills

Python

Async APIs

LLM prompting

Tool calling

Structured outputs

Pydantic

JSON Schema

LangGraph

RAG systems

LoRA/QLoRA

Multi-GPU fine-tuning

LLM evaluation

Guardrails

Distributed systems

Education

Bachelor’s or Master’s in Computer Science

Tools

LangGraph

Pydantic

JSON Schema

Job description

ELEMYNT, built by Xora Innovation, seeks a senior engineer to own LLM systems behind our platform, from model internals to production services. Expect hands-on coding, evaluation, tracing, and delivering reliable capabilities across customer environments.

You will enable tool calling, multi-step planning, and robust retrieval with embeddings and RAG techniques while maintaining guardrails and cost controls.