Backend ML Engineer: Scale AI Infra & LLM Pipelines

Sterling; North Sioux City (SD); On-site; USD 120,000 - 180,000; Full time

Job summary

Sterling Computers is seeking a Backend ML Engineer to take AI/ML systems from prototype to production, designing inference APIs, building retrieval and orchestration pipelines, and integrating large language models. The role requires 3–5 years in backend or ML engineering, Python (FastAPI/Flask), cloud experience (AWS, GCP, or Azure), and hands-on work with LLMs and vector databases.

Travel up to 25%. Join a collaborative team delivering AI features for government and commercial clients,

Qualifications

• Bachelor’s degree in Computer Science, Machine Learning, or related field or equivalent practical experience.

Responsibilities

• Build, test, and maintain production ML services — inference APIs, retrieval pipelines, orchestration layers, evaluation components.
• Design scalable RESTful and streaming APIs that serve ML model outputs under real-world load.
• Integrate and tune LLMs, embedding models, and rerankers across hosted and self-hosted options; balance cost, latency, and quality.
• Build ingestion and chunking pipelines for unstructured data and maintain vector store schemas for multi-tenant retrieval.
• Implement evaluation harnesses to measure retrieval quality, generation faithfulness, and end-to-end accuracy; close loop from evals to improvements.
• Containerize and deploy ML workloads with Docker and Kubernetes; manage resources and versioning.
• Optimize queries, vector search, and caching to reduce latency and cost.
• CI/CD for ML services and monitoring for system and ML-specific metrics.
• Collaborate with frontend engineers, ML researchers, and product analysts to ship features.
• Document backend and ML infrastructure, including model cards and decisions.
• Travel - up to 25–50%.

Skills

Python (FastAPI/Flask)

PyTorch

Transformers

Sentence Transformers

AWS/GCP/Azure

LLM integration

Vector databases

RAG patterns

Async APIs

Education

Bachelor's in CS/ML

Tools

MLflow

Weights & Biases

Kubeflow

LangChain

Job description

Sterling Computers is seeking a Backend ML Engineer to take AI/ML systems from prototype to production, designing inference APIs, building retrieval and orchestration pipelines, and integrating large language models. The role requires 3–5 years in backend or ML engineering, Python (FastAPI/Flask), cloud experience (AWS, GCP, or Azure), and hands-on work with LLMs and vector databases.

Travel up to 25%. Join a collaborative team delivering AI features for government and commercial clients,