LLMOps Platform Engineer (Seattle)SumerSports • Seattle, WA, United States

LLMOps Platform Engineer (Seattle)

SumerSports • Seattle, WA, United States

job_description.job_card.variable_hours_ago

serp_jobs.job_preview.job_type

serp_jobs.job_card.full_time

job_description.job_card.job_description

About SmerSports

SmerSports is building the leading AI-powered sports intelligence platform combining cutting-edge deep learning models (video structured game data) with LLM-based reasoning systems that deliver real-time insights to teams, coaches, players, analysts, and fans.

Were reimagining how football and sports at large are understood and optimized.

Role Overview

As an ML / AI Engineer on the LLMOps Platform team , youll build the core infrastructure that powers our AI-first product organization.

Youll design, implement, and scale the systems that make it possible for product pods to develop, evaluate, and safely deploy LLM-based and multimodal applications from RAG pipelines and model gateways to eval frameworks and cost-optimized serving.

Youll work closely with AI app engineers, full-stack engineers, and the Deep Learning Research group to ensure every AI system we ship is fast, grounded, and reliable.

What Youll Do

Build and operate the LLM Platform

Develop model routing, prompt registry, and orchestration services for multi-model workflows.
Integrate external LLM APIs (OpenAI, Anthropic, Mistral) and internal fine-tuned models.

Enable fast, safe experimentation

Implement automated evaluation pipelines (offline + online) with golden sets, rubrics, and regression detection.

Support CI / CD for prompt and model changes, with rollback and approval gates.

Collaborate cross-functionally

Partner with product pods to instrument RAG pipelines and prompt versioning.

Work with deep learning and data teams to integrate structured and unstructured retrieval into LLM workflows.

Optimize performance and cost

Profile latency, token usage, and caching strategies.

Build observability and monitoring for LLM calls, embeddings, and agent behaviors.

Ensure reliability and safety

Implement guardrails (toxicity, PII filters, jailbreak detection).

Maintain policy enforcement and audit logging for AI usage.

What Were Looking For

Required

5+ years of experience in applied ML, NLP, or ML infrastructure engineering.

Strong coding skills in Python and experience with frameworks like LangChain, LlamaIndex, or Haystack.

Solid understanding of retrieval-augmented generation (RAG), embeddings, vector databases, and evaluation methodologies.

Experience deploying models or AI systems in production environments (AWS, GCP, or Azure).

Familiarity with prompt management, LLM observability, and CI / CD automation for AI workflows.

Preferred

Experience with model serving (vLLM, Triton, Ray Serve, KServe).

Understanding of LLM evaluation frameworks (OpenAI Evals, Promptfoo, Arize Phoenix, TruLens).

Background in sports analytics, data engineering, or multimodal (video / text) systems.

Exposure to Responsible AI practices (guardrails, safety evals, fairness testing).

Youll Thrive Here If You

Think of LLMs as both tools and teammates and know how to use them deterministically.

Get energy from building paved roads that help other engineers move faster.

Enjoy balancing research-grade experimentation with production reliability.

Want to help redefine how the world understands sports through AI.

Why Join

Youll help architect the backbone of a next-generation AI platform that fuses deep learning and large language models to make sense of the most complex, dynamic data in sports.

Your work will directly impact elite teams, broadcast partners, and fans while setting new standards for how AI is built and operated in production.

serp_jobs.job_alerts.create_a_job

Platform Engineer • Seattle, WA, United States