AI Engineer

DeepRec.ai; New York (NY); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Competitive base salary

Equity

Health, dental, and vision coverage

Flexible PTO

Home workspace setup

Office meals, snacks, and drinks

Location-appropriate benefits

Job summary

DeepRec.ai is building a learning system that helps AI agents understand how enterprises operate by ingesting knowledge bases, conversations, tickets, and system activity to create structured instructions for AI agents with built-in confidence and control.

The team designs and deploys LLM-powered workflows, builds autonomous agents for knowledge management, and develops reliability, evaluation, and product direction in a fast-paced, in-person environment.

Qualifications

• Experience building complex, production LLM-based systems, and the ability to speak to the engineering decisions and tradeoffs behind them
• A track record of shipping meaningful software or AI systems to production and iterating on them based on real-world usage
• Experience building agents, autonomous systems, or sophisticated LLM workflows
• Genuine interest in systems that improve continuously through human feedback, evaluation, prompt optimization, and context engineering
• Comfort operating at the boundary between AI research and production engineering
• Strong systems-design chops, particularly with asynchronous and distributed architectures
• Excellent written and verbal communication — able to explain technical concepts to both technical and non-technical stakeholders
• 3+ years of professional engineering experience

Responsibilities

• Building and extending a core context-learning platform, turning real customer problems into reusable AI capabilities
• Designing and implementing LLM-powered systems and agentic workflows from concept through production
• Building autonomous agents for knowledge management — systems that can create, edit, update, and maintain large knowledge bases
• Developing reliability and confidence mechanisms, including evaluation frameworks and decision logic for automate-vs-escalate calls
• Architecting asynchronous, scalable infrastructure to support complex AI orchestration
• Building systems that learn and improve through human feedback, evaluation, and iterative optimization
• Contributing to the company's AI strategy, technical architecture, and product direction

Job description

DeepRec.ai is representing a rapidly growing, venture-backed AI company that's building technology to help enterprises understand, improve, and automate complex business processes. Our client's team brings together experienced engineers, AI researchers, and operators with backgrounds building sophisticated AI systems at scale, and they place a premium on technical depth, intellectual curiosity, ownership, and a first-principles approach to hard problems.

The Opportunity

Our client is building a learning system that helps AI agents understand how enterprises actually operate. Their platform ingests information from sources like knowledge bases, conversations, support tickets, and system activity, then converts it into structured instructions that AI agents can execute — with built-in confidence and reliability mechanisms that determine when an agent should act autonomously versus loop in a human.

What You'd Be Doing

• Building and extending a core context-learning platform, turning real customer problems into reusable AI capabilities
• Designing and implementing LLM-powered systems and agentic workflows from concept through production
• Building autonomous agents for knowledge management — systems that can create, edit, update, and maintain large knowledge bases
• Developing reliability and confidence mechanisms, including evaluation frameworks and decision logic for automate-vs-escalate calls
• Architecting asynchronous, scalable infrastructure to support complex AI orchestration
• Building systems that learn and improve through human feedback, evaluation, and iterative optimization
• Contributing to the company's AI strategy, technical architecture, and product direction

What Our Client Is Looking For

• Experience building complex, production LLM-based systems, and the ability to speak to the engineering decisions and tradeoffs behind them
• A track record of shipping meaningful software or AI systems to production and iterating on them based on real-world usage
• Experience building agents, autonomous systems, or sophisticated LLM workflows
• Genuine interest in systems that improve continuously through human feedback, evaluation, prompt optimization, and context engineering
• Comfort operating at the boundary between AI research and production engineering
• Strong systems-design chops, particularly with asynchronous and distributed architectures
• Excellent written and verbal communication — able to explain technical concepts to both technical and non-technical stakeholders
• 3+ years of professional engineering experience

Compensation & Benefits

• Competitive base salary and meaningful equity
• Comprehensive health, dental, and vision coverage
• Flexible PTO
• Support for setting up a home workspace
• Office meals, snacks, and drinks
• Additional location-appropriate benefits

Working Environment

This is a highly collaborative, fast-paced team with a strong emphasis on in-person collaboration.