Senior Software Engineer

Harnham; San Francisco (CA); On-site; USD 175,000 - 210,000; Full time

Benefits offered by this job

Competitive base + equity

Work on cutting-edge AI

High-impact role with ownership

Job summary

A fast-growing SaaS company in San Francisco is looking for a Senior AI Engineer to design and build scalable, production-grade AI systems. You will develop LLM-powered solutions and architect optimized AI systems. The role demands extensive software engineering experience, particularly in AI and LLM systems. This position offers a competitive salary with equity and is hybrid, allowing for collaboration in person on select days. Join an innovative environment to work on impactful AI technologies.

Qualifications

• 7+ years of software engineering experience.
• Building AI/LLM systems in production for at least 2 years.
• Experience with RAG, vector databases, and LLM evaluation.

Responsibilities

• Design and deploy LLM-powered systems.
• Build retrieval-augmented generation (RAG) pipelines.
• Architect scalable AI systems optimized for performance.

Skills

7+ years SWE

2+ years building AI/LLM systems

Experience with RAG

Solid system design

Job description

SENIOR AI ENGINEER — AGENTIC SYSTEMS + GENAI

$175K – $210K BASE + EQUITY

HYBRID — SAN FRANCISCO (TUES–THURS)

Are you excited about building production-grade AI systems that power real-world, high-stakes decisions—not just prototypes?

Do you want to work on agentic AI, LLM reasoning, and scalable AI infrastructure at a company with proven product-market fit and strong growth?

THE COMPANY

A fast-growing, venture-backed SaaS company in the compliance and security space, helping organizations build trust at scale.

• Rapid growth and expanding into enterprise customers
• Investing heavily in AI-powered product capabilities
• Building next-gen platform with automation, LLMs, and agentic workflows

THE ROLE

As a Senior AI Engineer, you’ll build scalable, production-grade AI systems embedded into core products.

• Design and deploy LLM-powered systems with reasoning and decision support
• Build RAG pipelines (retrieval, embeddings, reranking, evaluation)
• Develop agentic workflows with tools, retrieval, and human-in-the-loop
• Architect scalable AI systems optimized for latency, cost, and reliability

YOUR SKILLS AND EXPERIENCE

• 7+ years SWE + 2+ years building AI/LLM systems in production
• Experience with RAG, vector databases, and LLM evaluation
• Solid system design + ability to ship end-to-end solutions

THE BENEFITS

• Competitive base + equity
• Hybrid in SF
• Work on cutting-edge AI (agentic systems, RAG, LLMs)
• High-impact role with strong ownership and visibility