Senior AI Engineer (Agentic Systems & LLM Applications)

Senior AI Engineer (Agentic Systems & LLM Applications)

San Francisco, CA (Hybrid — Tuesday to Thursday onsite)

$180,000 – $220,000 base + equity + benefits

About the Company

This organization builds software that helps businesses operate with greater transparency, accountability, and trust. Its platform supports critical workflows around governance, risk, and operational decision-making, enabling teams to manage complex processes with speed and confidence.

The company has reached meaningful scale and is now investing heavily in its next phase — embedding advanced AI directly into core product workflows. This is not an experimentation layer; these are production systems that customers rely on to make real decisions.

Engineering teams operate with high ownership and low overhead. The environment rewards people who take initiative, challenge assumptions, and deliver systems that work in the real world.

About the Role

This is a high-ownership, builder role for engineers who want to push beyond “feature-level AI” and design systems that actually reason, act, and operate in production.

You will own end-to-end development of AI systems — from architecture and design through deployment, evaluation, and iteration. The focus is on building agentic systems and retrieval-driven pipelines that can handle complex, multi-step workflows across large volumes of structured and unstructured data.

This role is best suited for engineers who have already shipped LLM-based systems and want to go deeper — improving system reliability, designing evaluation frameworks, and building AI that can be trusted in high-stakes environments.

You’ll work closely with product and engineering leadership to define what gets built, not just how it gets built.

Key Responsibilities • Architect and deploy production LLM systems capable of multi-step reasoning and decision support • Build and scale agentic workflows that automate complex, long-running processes • Design end-to-end RAG pipelines (ingestion, embeddings, retrieval, ranking, generation) • Develop evaluation frameworks and guardrails to ensure system accuracy, reliability, and safety • Optimize systems for latency, cost efficiency, and production performance • Partner with product and engineering leaders to identify and prioritize high-impact AI opportunities • Contribute to backend systems and infrastructure supporting large-scale AI deployment

Must Haves • 7+ years of software engineering experience, including 2+ years building AI/ML systems • Strong Python expertise and experience building production-grade systems • Proven track record shipping LLM-based applications into production • Hands-on experience with RAG pipelines, embeddings, and vector databases • Experience building agent-based or multi-step AI systems • Strong system design skills with experience in distributed systems • Clear ownership of systems from initial concept through production and iteration

Nice to Have • Experience with workflow orchestration or distributed task systems • Familiarity with backend systems or TypeScript-based services • Experience working with document-heavy or high-complexity datasets • Exposure to evaluation frameworks, monitoring systems, or AI safety practices

Why Join • Build AI systems that operate in real-world, high-stakes environments — not prototypes • Own the architecture and evolution of agentic systems used by real customers • Work on problems where correctness, reliability, and trust actually matter • High autonomy with direct influence on product direction and technical strategy • Strong compensation, meaningful equity, and comprehensive benefits • In-person collaboration Tuesday–Thursday with a focused, high-caliber engineering team • Opportunity to raise the technical bar alongside engineers who have shipped real systems