Real-Time ML Engineer: Memory Retrieval & Production

Engramme; San Francisco (CA); On-site; USD 140,000 - 200,000; Full time

Job summary

Engramme in San Francisco, CA is seeking a Machine Learning Engineer to design and deploy scalable ML systems focused on memory retrieval and contextual understanding. You will build production-ready ML infrastructure, training pipelines, and real-time optimization for latency.

The role involves vector databases, embeddings, and collaboration with research teams to productionize new algorithms. The ideal candidate has 4+ years of ML engineering experience, strong Python skills with

Qualifications

• 4+ years of machine learning engineering experience.
• Strong proficiency in Python and ML frameworks, including PyTorch and TensorFlow.
• Experience deploying ML models into production environments.
• Knowledge of MLOps, model serving, and monitoring.
• Understanding of NLP, embeddings, and retrieval systems.
• Experience with cloud platforms such as AWS and GCP, and containers.
• Strong software engineering fundamentals.
• Experience with large-scale data processing.

Responsibilities

• Design and implement ML models for memory retrieval and ranking.
• Build ML infrastructure and training pipelines.
• Deploy and monitor models in production at scale.
• Optimize model performance and latency for real-time systems.
• Work with vector databases and embedding systems.
• Apply MLOps best practices, including monitoring and operational readiness.
• Collaborate with the research team to productionize new algorithms.

Skills

4+ years

Python

PyTorch

TensorFlow

ML deployment

MLOps

model serving

monitoring

NLP

embeddings

retrieval systems

AWS

GCP

Containers

vector databases

Tools

Python

PyTorch

TensorFlow

AWS

GCP

Containers

Job description

Engramme in San Francisco, CA is seeking a Machine Learning Engineer to design and deploy scalable ML systems focused on memory retrieval and contextual understanding. You will build production-ready ML infrastructure, training pipelines, and real-time optimization for latency.

The role involves vector databases, embeddings, and collaboration with research teams to productionize new algorithms. The ideal candidate has 4+ years of ML engineering experience, strong Python skills with