Frontier Agents Engineer (Applied AI)

About the Role

Scale AI is the data foundation for AI, helping organizations build and deploy reliable production AI applications. We partner with the world's leading enterprises and government organizations to accelerate their AI transformation through frontier AI systems that solve real business problems.

As a Frontier Agent Engineer (Applied AI), you'll bridge the gap between cutting-edge AI research and production deployment. You'll work directly with enterprise customers to design, evaluate, and deploy intelligent systems that combine frontier models with structured knowledge, retrieval, traditional machine learning, and enterprise software. Unlike traditional ML roles, you'll work across a diverse portfolio of AI challenges spanning multiple industries and use cases.

Responsibilities

• Design and deploy production AI agents leveraging the latest advances in large language models, reasoning, retrieval, memory, and tool use.
• Architect intelligent systems combining LLMs, traditional machine learning, structured knowledge, enterprise data, and deterministic software into reliable production workflows.
• Engineer customer intelligence layers, retrieval pipelines, memory systems, and knowledge representations for agent reasoning over large, heterogeneous enterprise data.
• Develop multi-agent systems coordinating reasoning, planning, tool execution, and human oversight.
• Translate frontier AI research into production systems by evaluating new models, prompting techniques, reasoning paradigms, and agent architectures.
• Own the full experimentation lifecycle, from hypothesis generation to production rollout.
• Design rigorous evaluation frameworks using offline benchmarks, online A/B experiments, golden datasets, regression suites, LLM-as-a-Judge, and human evaluation.
• Run controlled experiments and ablation studies to understand contributions of different models, prompts, retrieval strategies, reasoning techniques, and agent architectures.
• Continuously evaluate newly released frontier models for quality, latency, reliability, or cost improvements.
• Develop confidence estimation, reflection, and continuous learning systems improving agents over time using real-world feedback.
• Build production-quality AI systems with emphasis on reliability, observability, latency, safety, and cost.
• Design agent guardrails, fallback strategies, tracing, monitoring, and evaluation pipelines for safe deployment in high-stakes environments.
• Collaborate with infrastructure engineers to deploy AI systems securely within enterprise cloud environments.
• Build human-in-the-loop workflows combining AI automation with expert oversight.
• Partner directly with enterprise customers to understand their business, data, and operational challenges.
• Translate ambiguous customer problems into production AI architectures.
• Rapidly prototype new ideas, validate them with customers, and evolve successful solutions into scalable production systems.
• Identify reusable patterns that become core capabilities across enterprise deployments.

Qualifications

Required

• 4+ years of software engineering, machine learning, or applied AI experience.
• Strong Python programming skills.
• Experience building production AI systems using LLMs.
• Experience with modern AI tooling, including OpenAI, Claude, MCP, agent frameworks, vector databases, or retrieval systems.
• Strong understanding of machine learning fundamentals and modern language models.
• Experience designing or evaluating AI systems using quantitative metrics.
• Excellent communication skills and ability to work directly with enterprise customers.

Preferred

• Applied AI: Experience building production AI agents or autonomous systems.
• Deep understanding of reasoning, retrieval, memory, planning, and tool use.
• Experience designing evaluation frameworks for LLMs and agentic systems.
• Experience with RAG, semantic search, knowledge graphs, customer intelligence systems, or structured knowledge representations.
• Experience with fine-tuning, distillation, reinforcement learning, small language models, or model optimization.
• Familiarity with multimodal AI systems and frontier foundation models.
• Software Engineering: Experience building distributed production systems.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Experience with Docker, Kubernetes, CI/CD, and production observability.
• Experience integrating AI systems into enterprise software environments.
• Customer Engineering: Experience working directly with enterprise customers.
• Ability to translate ambiguous business problems into technical architectures.
• Strong written and verbal communication skills.
• Experience leading technical workshops, architecture reviews, or customer design sessions.

What Makes This Role Different

• Work across the full lifecycle of modern AI systems: designing reasoning architectures, building retrieval/memory systems, developing predictive models, running experiments, shipping production systems, measuring business impact, and continuously improving agents.
• Solve diverse AI problems across industries, datasets, model architectures, and agentic systems to rapidly develop intuition for successful production AI systems.

Benefits

• Comprehensive health, dental, and vision coverage.
• Retirement benefits.
• Learning and development stipend.
• Generous PTO.
• Commuter stipend (role-dependent).

Pay

The base salary range for this full-time position in San Francisco, New York, or Seattle is $180,000—$225,000 USD. Compensation packages include base salary, equity, and benefits, determined during the interview process based on work location, job-related skills, experience, qualifications, interview performance, and relevant education or training.