Senior AI Product Engineer - Full-Stack LLM Solutions

Harnham; San Francisco (CA); Hybrid; USD 200,000 - 250,000; Full time

Benefits offered by this job

Employer-paid health, dental, and vision coverage

401(k) with company match

Hybrid flexibility with SF office

Job summary

Harnham is seeking a Senior AI Product Engineer in San Francisco to build and ship AI-powered user experiences. You will design and implement backend and frontend features using Node.js, TypeScript, and React, while working closely with product and design teams.

The ideal candidate has 2+ years of software engineering experience and a strong understanding of Python for AI systems. This role offers a hybrid work model and a competitive salary with equity options.

Qualifications

• 2+ years of software engineering experience, including shipping customer-facing products end-to-end.
• Strong full-stack experience with Node.js, TypeScript, and React.
• Experience building and deploying LLM-powered features.

Responsibilities

• Design, build, and ship end-to-end product features powered by LLMs.
• Translate AI capabilities into intuitive product experiences.
• Own the full lifecycle of AI features: prototyping, productionization, and iteration.

Skills

Node.js and TypeScript

React

Python for AI/ML

End-to-end software engineering

Building LLM-powered features

Tools

Vector databases (Pinecone, FAISS, Chroma)

Orchestration frameworks (Temporal, Airflow)

Job description

Senior AI Product Engineer (Full Stack) | Series C GRC Startup | San Francisco (Hybrid)

Location: San Francisco, CA (Hybrid – 3 days/week in office)

Compensation: $200,000 – $250,000 base salary + significant equity

The Rol

eThis is a product-minded, full-stack engineering role focused on building and shipping AI-powered user experiences end-to-end. You’ll own the intersection of AI systems and product delivery—turning LLM capabilities into intuitive, reliable, and high-impact features used by enterprise customers

.You’ll work across Node.js/TypeScript backends, Python-based AI services, and React frontends to bring AI into real workflows. This role is ideal for someone who cares as much about product quality, usability, and iteration speed as they do about model performance and system design

.
What You’ll

• DoDesign, build, and ship end-to-end product features powered by LLMs, from backend services (Node.js/TypeScript, Python) to frontend interfaces (Reac
• t)Translate AI capabilities (RAG, agents, retrieval systems) into intuitive product experiences that solve real customer proble
• msOwn the full lifecycle of AI features: prototyping, productionization, monitoring, and iteration based on user feedba
• ckBuild scalable APIs and services that integrate LLM pipelines, vector search, and orchestration layers into the core produ
• ctDevelop responsive, high-quality React interfaces that surface AI outputs in clear, actionable wa
• ysImplement human-in-the-loop workflows directly into product experiences to support trust, auditability, and contr
• olPartner closely with product, design, and GTM teams to define requirements, prioritize features, and iterate quick
• lyEstablish best practices for shipping AI features in production, balancing performance, latency, cost, and

UX
Requireme

• nts2+ years of software engineering experience, including experience shipping customer-facing products end-to-
• endStrong full-stack experience: Node.js + TypeScript (backend APIs/services) and React (fronte
• nd)Solid hands-on experience with Python for AI/ML systems in product
• ionExperience building and deploying LLM-powered features (RAG, embeddings, vector search, reranking, or agen
• ts)Proven ability to take ambiguous product ideas and turn them into shipped, user-facing featu
• resStrong product intuition: ability to balance technical tradeoffs with user experience and business imp

act
Nice to

• HaveExperience building AI features in regulated or enterprise environments (GRC, security, complia
• nce)Familiarity with vector databases (Pinecone, FAISS, Chroma) and modern AI tooling ecosys
• temsExperience with orchestration frameworks (Temporal, Airflow) or event-driven architect
• uresExposure to analytics/data platforms (Snowflake,
• dbt)Experience with AI evaluation and feedback loops integrated into product workf

lows
Compensation and Ben

• efits$200,000 – $250,000 base salary + significant equity at Ser
• ies CEmployer-paid health, dental, and vision coverage for employee and depen
• dents401(k) with company
• matchHybrid flexibility with a collaborative SF home