ML Engineer: Memory & Vector Retrieval

ENGRAM Lab; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

ENGRAM Lab is seeking an experienced ML Engineer to build and deploy memory retrieval models and scalable ML infrastructure. You will design and implement models, train pipelines, and deploy them to production at scale, ensuring real-time performance and robust monitoring.

Collaboration with the research team will help productionize new algorithms. The role emphasizes NLP, embeddings, and retrieval systems, with hands-on work on cloud platforms (AWS, GCP) and containerized environments to drive

Qualifications

• 4+ years of ML engineering experience.
• Proficiency in Python and ML frameworks (PyTorch, TensorFlow).
• Experience deploying ML models to production.
• Knowledge of MLOps, model serving, and monitoring.
• Understanding of NLP, embeddings, and retrieval systems.
• Experience with cloud platforms (AWS, 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.
• Implement MLOps best practices and monitoring.
• Collaborate with research team to productionize new algorithms.

Skills

ML engineering

Production deployment

MLOps

NLP embeddings retrieval

Software fundamentals

Large-scale data processing

Tools

PyTorch

TensorFlow

AWS

GCP

Docker

Kubernetes

Job description

ENGRAM Lab is seeking an experienced ML Engineer to build and deploy memory retrieval models and scalable ML infrastructure. You will design and implement models, train pipelines, and deploy them to production at scale, ensuring real-time performance and robust monitoring.

Collaboration with the research team will help productionize new algorithms. The role emphasizes NLP, embeddings, and retrieval systems, with hands-on work on cloud platforms (AWS, GCP) and containerized environments to drive