LLM Platform Engineer: RAG & Multimodal AI

Schemata Inc.; San Francisco, Northern (CA, KY); Hybrid; USD 140,000 - 210,000; Full time

Benefits offered by this job

Competitive salary

Meaningful equity stake

Comprehensive health coverage

401(k) plan

Paid parental leave

High visibility and real impact

Job summary

Schemata Inc. is seeking a highly skilled LLM Platform Engineer to design, build and optimize AI systems that turn diverse data into real-time guidance for training and maintenance applications.

You will own end-to-end deployment across cloud, on-premises and air-gapped environments, ensuring low latency and reliable performance in regulated industries. This senior role emphasizes production-grade ML systems and cross-functional collaboration.

Qualifications

• 4+ years of software engineering experience.
• Experience building production LLM systems (RAG pipelines, agents, or LLM-powered products).
• Hands-on experience with knowledge ingestion and retrieval systems.
• Strong Python and backend engineering fundamentals.
• Experience deploying and operating production systems: CI/CD, release management, monitoring.

Responsibilities

• Design and build multimodal knowledge base ingestion pipelines.
• Improve retrieval-augmented generation (RAG) systems including chunking, indexing, and grounding.
• Build knowledge base lifecycle with versioning, SME corrections, and validation.
• Scale the feedback loop using user signals to improve retrieval and content.
• Own deployment and delivery lifecycle across cloud, on-premises and air-gapped environments.
• Strengthen AI feature reliability and latency through profiling, caching, and graceful degradation.
• Collaborate with spatial computing, mobile, and product engineers to connect knowledge base with 3D scene representations.
• Lead the end-to-end from evaluation to production inference and optimization.
• 4+ years of software engineering experience, with at least 1–2 years building production LLM systems.

Skills

LLM system design

RAG pipelines

multimodal retrieval

Python programming

backend systems

cloud computing

metrics-driven development

production systems

CI/CD

monitoring

Tools

AWS

CI/CD pipelines

GPU serving

Job description

Schemata Inc. is seeking a highly skilled LLM Platform Engineer to design, build and optimize AI systems that turn diverse data into real-time guidance for training and maintenance applications.

You will own end-to-end deployment across cloud, on-premises and air-gapped environments, ensuring low latency and reliable performance in regulated industries. This senior role emphasizes production-grade ML systems and cross-functional collaboration.