Job Description
Job DescriptionAbout the Role
This is a founding-level, senior individual contributor role at a Series A AI compliance SaaS company building the system of record for enterprise marketing and packaging review. The platform automates high-stakes compliance workflows — turning manual, multi-week approval cycles into hours — for large regulated-industry brands.
As a Senior Applied AI Engineer focused on Agentic Systems, you will own the core technical moat: the deterministic orchestration layer and safety infrastructure that makes enterprise-grade AI compliance trustworthy at scale. You are not building demos — you are building auditable, production-grade systems where correctness is non-negotiable.
This is a hybrid, in-office role based in San Francisco, CA (3 days/week in-office). You will work directly alongside a small, senior engineering team at a critical architectural inflection point.
What You'll Do
-
Agentic Reasoning & Orchestration: Design and evolve multi-agent LLM systems that decompose complex review tasks into reliable, auditable steps. Define agent responsibilities, hand-offs, and termination conditions to minimize reasoning drift and maximize consistency.
-
Context, Retrieval & Memory Systems: Architect retrieval pipelines using RAG, structured memory, and graph-based retrieval approaches to supply agents with the right context at the right time. Balance recall, precision, and latency across large knowledge bases (brand guidelines, regulations, historical decisions).
-
Stateful, Asynchronous Workflows: Own long-running, fault-tolerant workflows using Temporal (or similar), ensuring retries, versioning, and determinism across non-deterministic model calls. Treat agent orchestration as a distributed systems problem — managing state, failures, and observability.
-
Evaluation, Safety & Reliability: Build evaluation frameworks using statistical metrics, gold labels, and automated regression testing to prove system reliability. Prioritize correctness and trust, especially in high-risk legal and compliance scenarios.
-
Asset Understanding Pipeline: Collaborate on image and document preprocessing (OCR, layout analysis, Vision Language Models) to ensure downstream agents receive structured, machine-readable context.
What We're Looking For
Required
-
7+ years of professional software/ML engineering experience
-
Minimum 2-year average tenure across roles, with a clear track record of career progression and promotions
-
Demonstrated expertise architecting multi-agent AI systems: agent role design, multi-step reasoning flows, tool integration, memory/retrieval architectures, and deterministic/auditable workflows
-
Hands-on experience with LLM orchestration frameworks and stateful workflow engines (e.g., Temporal, Prefect, or equivalent)
-
Strong background in retrieval-augmented generation (RAG) and vector/graph-based retrieval systems
-
Experience building and owning production-grade evaluation and safety frameworks for AI systems
-
Startup experience or equivalent experience in CPG, regulated industries, or enterprise compliance domains
-
Must be eligible to work in the United States without visa sponsorship
-
Able and willing to work in-office in San Francisco, CA at least 3 days per week
Nice to Have
-
Experience with vision-language models (VLMs), OCR pipelines, or document layout analysis
-
Background in marketing technology, packaging compliance, or regulatory tech (regtech)
-
Familiarity with enterprise compliance workflows or brand governance processes
-
Prior experience as a founding or early-stage engineer
Compensation & Benefits
-
Base salary: $185,000 – $210,000 per year
-
Equity participation (early-stage, Series A)
-
Hybrid work flexibility (3 days in-office, remainder remote)
Visa sponsorship is not available for this role. Candidates must be authorized to work in the United States.
Location
San Francisco, CA, United States — Hybrid (3 days/week in-office required). Some remote flexibility on remaining days.