Senior ML Engineer: Real-Time RAG & LLM Systems

Tekmetric; Houston (TX); Hybrid; USD 120,000 - 190,000; Full time

Benefits offered by this job

Health insurance

401(k) with match

Generous PTO and paid parental leave

Job summary

Tekmetric, a Houston-based, cloud-native auto repair software leader, seeks an ML Engineer to build scalable AI features. You will own RAG pipelines, semantic search, and end-to-end recommendation models, collaborating with data engineers to integrate models into our data pipelines and product workflows.

We prize hands-on experience, ownership, and a bias for action. This role offers hybrid and remote work options and opportunities to impact thousands of auto shops nationwide.

Qualifications

• 4+ years in ML engineering with production experience.
• Experience taking ML features from experiments to production.
• Strong background in retrieval and vector-based search.
• Hands-on with RAG, tool use, and prompt engineering.

Responsibilities

• Design and build RAG pipelines and context for LLM-powered features.
• Own semantic search infrastructure over operational data.
• Develop end-to-end recommendation models and inference paths.
• Collaborate with engineers to integrate ML into data pipelines.

Skills

ML engineering

Retrieval systems

LLM patterns

Python tooling

AWS SageMaker/Bedrock

Tools

SageMaker

Bedrock

S3/Lambda

PyTorch

LangChain

FAISS

Pinecone

Job description

Tekmetric, a Houston-based, cloud-native auto repair software leader, seeks an ML Engineer to build scalable AI features. You will own RAG pipelines, semantic search, and end-to-end recommendation models, collaborating with data engineers to integrate models into our data pipelines and product workflows.

We prize hands-on experience, ownership, and a bias for action. This role offers hybrid and remote work options and opportunities to impact thousands of auto shops nationwide.