Senior AI Engineer

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

Job summary

Empathy Talent partners with a fast-growing tech company to hire a Senior AI Engineer who will lead production AI systems from concept to production. You’ll design agentic architectures, build evaluation frameworks, and ship reliable AI experiences at scale.

You will own AI capabilities across development, deployment, reliability, and observability, balancing model intelligence with stable software behavior.

Qualifications

• 3–6+ years of professional software engineering experience building complex production systems.
• Strong experience with Python and/or TypeScript.
• Experience with relational databases such as Postgres.
• Demonstrated experience shipping LLM-powered products or features into production.
• Hands-on experience building AI agents, agent orchestration, or multi-step LLM workflows.
• Experience with retrieval pipelines, embeddings, vector databases, and RAG architectures.
• Familiarity with leading foundation-model APIs and modern AI development tooling.
• Strong understanding of production software architecture, APIs, data systems, observability, and reliability.

Responsibilities

• Build Production AI Systems.
• Design and build agentic systems that automate complex workflows.
• Orchestrate LLMs, tools, retrieval systems, APIs, and business logic into production-grade apps.
• Own AI capabilities throughout lifecycle: development, deployment, reliability, performance, observability.
• Balance model intelligence with predictable software behavior.
• Develop and optimize agent orchestration, tool use, and reasoning workflows.
• Build evaluation frameworks, feedback loops, and guardrails to improve AI performance.
• Design prompts, retrieval pipelines, and orchestration logic.
• Work with vector databases, embeddings, and modern LLM APIs.
• Prototype rapidly and turn concepts into scalable systems.

Skills

3–6+ years software engineering

Python

TypeScript

Postgres

LLM-powered products

AI agents

agent orchestration

retrieval pipelines

vector databases

LLM APIs

Tools

LLM APIs

Vector databases

Retrieval pipelines

Embeddings

RAG architectures

Job description

We’re partnering with a fast-growing technology company that is building sophisticated AI-powered products used in complex, high-stakes business environments. They’re looking for a Senior AI Engineer who can take meaningful product areas from concept through production—designing agentic systems, building evaluation frameworks, and shipping reliable AI experiences at scale.

This is a hands-on engineering role for someone who has already shipped LLM-powered products into production and wants significant ownership over architecture, product decisions, and execution.

What You’ll Own

Build Production AI Systems

• Design and build agentic systems that automate complex, multi-step workflows.
• Translate real-world user problems into reliable AI behaviors and system architectures.
• Orchestrate LLMs, tools, retrieval systems, APIs, and business logic into production-grade applications.
• Own AI capabilities throughout their lifecycle, including development, deployment, reliability, performance, and observability.
• Build systems that balance model intelligence with predictable software behavior.
• Develop and optimize agent orchestration, tool use, retrieval, and reasoning workflows.
• Build evaluation frameworks, feedback loops, and guardrails to continuously improve AI performance.
• Design and optimize prompts, retrieval pipelines, context management, and orchestration logic.
• Work with vector databases, embeddings, RAG architectures, and modern LLM APIs.
• Prototype rapidly and turn successful concepts into scalable, production-ready systems.

Drive Product Impact

• Partner closely with Product, Design, and Engineering to turn customer problems into technical solutions.
• Make thoughtful trade-offs around architecture, speed, reliability, and customer impact.
• Identify opportunities where AI can materially improve existing workflows or unlock entirely new capabilities.
• Take ownership of ambiguous problems and drive them from initial concept through production.
• Stay close to how users interact with the product and use those insights to improve the system.

Raise the Engineering Bar

• Provide thoughtful code reviews, architectural feedback, and technical mentorship.
• Build reusable abstractions, tooling, and patterns that improve engineering velocity.
• Help establish best practices around AI engineering, evaluation, reliability, and production deployment.
• Share technical learnings and help other engineers become more effective working with AI systems.

What We’re Looking For

You’re a strong software engineer who has adapted your engineering approach for an AI-native environment. You enjoy building quickly but understand that production AI requires rigorous engineering, evaluation, and reliability.

You likely bring:

• 3–6+ years of professional software engineering experience building complex production systems.
• Strong experience with Python and/or TypeScript.
• Experience working with relational databases such as Postgres.
• Demonstrated experience shipping LLM-powered products or features into production.
• Hands-on experience building AI agents, agent orchestration, or multi-step LLM workflows.
• Experience with retrieval pipelines, embeddings, vector databases, and RAG architectures.
• Familiarity with leading foundation-model APIs and modern AI development tooling.
• Strong understanding of production software architecture, APIs, data systems, observability, and reliability.
• Ability to operate effectively in ambiguous, fast-moving environments.
• Strong product instincts and the ability to think beyond implementation to the actual user outcome.

The Ideal Profile

We’re especially interested in engineers who combine strong traditional software engineering fundamentals with hands-on applied AI experience.

You don’t just experiment with LLMs—you’ve built with them, shipped them, evaluated them, and dealt with the challenges that emerge once AI systems encounter real users and production traffic.

You’re comfortable moving quickly, taking ownership, and helping shape both the technical solution and the product itself.