Senior LLM Systems Engineer — Production AI & Agents

Xora Innovation; San Diego (CA); Hybrid; USD 150,000 - 210,000; Full time

Job summary

ELEMYNT, built by Xora Innovation, seeks a seasoned engineer to own LLM-powered systems across production environments. You will design agents, implement tooling, and ensure safe, scalable, and observable services deployed in customer environments.

You will build end-to-end pipelines for model ingestion, evaluation, and deployment, including fine-tuning, retrieval, and robust monitoring in hybrid or on-site settings.

Qualifications

• Bachelor's or Master's in Computer Science or related engineering field and 5+ years shipping production software.
• Strong Python and reliability in async, HTTP and streaming APIs.
• Production experience with prompting, context engineering, tool calling, and structured outputs.
• Hands-on design and shipping of agents: loop, tools, memory, failure handling; LangGraph or equivalent.
• Experience building RAG systems: embeddings, chunking, hybrid search, reranking.
• Experience fine-tuning open-weight models (LoRA/QLoRA) on multi-GPU with curated data.
• Experience with LLM evaluation, guardrails, tracing, and production scoring.

Responsibilities

• Build and ship LLM-powered capabilities end to end from prototype to production.
• Design agents that plan multi-step work with tool calls and structured outputs.
• Create retrieval with embeddings, chunking, and hybrid search for context.
• Fine-tune open-weight models with multi-GPU setups and curated data.
• Develop evaluation loops with automated scoring and regression tracking.
• Instrument model calls and tooling with tracing for cost and reliability.
• Turn LLM capabilities into clean APIs and reusable engineering tooling.

Skills

Python

LLM systems in production

Async APIs

HTTP API design

Testing & code review

LangGraph

JSON Schema / Pydantic

RAG systems

Model fine-tuning (LoRA/QLoRA)

Tracing / observability

Education

Bachelor's or Master's in Computer Science or related engineering

Tools

LangGraph

Pydantic / JSON Schema

vLLM

TGI

SGLang

RAG tooling

Job description

ELEMYNT, built by Xora Innovation, seeks a seasoned engineer to own LLM-powered systems across production environments. You will design agents, implement tooling, and ensure safe, scalable, and observable services deployed in customer environments.

You will build end-to-end pipelines for model ingestion, evaluation, and deployment, including fine-tuning, retrieval, and robust monitoring in hybrid or on-site settings.