ML Engineer - Agent Infrastructure

Engram; San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

Engram is looking for a skilled software engineer to develop Monad, an agent runtime integrating memory and reasoning for AI systems in San Francisco. In this role, you will enhance the Monad DAG execution engine, manage agent workflows, and collaborate with research for memory capabilities.

The ideal candidate has over 5 years of software engineering experience with strong Python skills and expertise in machine learning systems. Join us to drive innovation across clinical research and cybersecurity.

Qualifications

• 5+ years experience in software engineering, with focus on ML systems.
• Strong Python skills; experience with async programming.
• Experience building production ML/AI systems at scale.

Responsibilities

• Build and maintain the Monad DAG execution engine.
• Implement trace logging and observability for agent workflows.
• Design tool integration patterns for domain-specific capabilities.
• Optimize inference latency and throughput for production workloads.
• Work closely with research to integrate new memory and reasoning capabilities.

Skills

Software engineering

Machine learning systems

Python

Distributed systems

Job description

We're building Monad, our agent runtime that orchestrates complex workflows with memory, reasoning, and tool integration. You'll own critical infrastructure that powers AI systems across clinical research, cybersecurity, and scientific computing.

What you'll do

• Build and maintain the Monad DAG execution engine
• Implement trace logging and observability for agent workflows
• Design tool integration patterns for domain-specific capabilities
• Optimize inference latency and throughput for production workloads
• Work closely with research to integrate new memory and reasoning capabilities

Requirements

• 5+ years experience in software engineering, with focus on ML systems
• Strong Python skills; experience with async programming
• Experience building production ML/AI systems at scale
• Understanding of LLM inference, tokenization, and prompting
• Familiarity with distributed systems and message queues

Nice to have

• Experience with agent frameworks (LangChain, AutoGPT, etc.)
• Background in compilers or runtime systems
• Contributions to open-source ML projects