2-8 years of software engineering experience in production user-facing or backend products.
Broad experience in AI/ML engineering, including deployment of LLM services and prompt design.
Full-stack proficiency in Python and TypeScript/React, with cloud experience in AWS or GCP.
Working knowledge of retrieval-augmented generation (RAG), vector databases, and retrieval pipelines.
Experience in building automated tests and monitoring for production AI systems.
Proven ability to design API-driven, high-throughput systems and real-time features.
Familiarity with workflow frameworks and orchestration tools, plus experience in regulated industries is a plus.
Responsibilities
Design and maintain systems for complex multi-step workflows across various industries.
Build and operate retrieval-augmented generation pipelines, including vector databases and domain-specific search.
Develop components for multi-agent orchestration, memory, and reasoning.
Create infrastructure to evaluate model performance and ensure reliability for enterprise use.
Ship full-stack AI products by designing APIs, implementing code, and managing production systems.
Support CI/CD processes, monitoring, and testing while collaborating with product and design teams.
Benefits
Opportunity to work in a pre-seed B2B SaaS environment with cutting-edge technology.
Engagement in diverse industries such as healthcare, legal, and fintech.
Hands-on experience with production AI services and complex workflows.
Collaborative team culture focused on user feedback and iterative development.
Full Job Description
Join the core product team at a pre-seed B2B SaaS company building agentic systems to automate complex workflows across enterprise and regulated industries. You will build and operate production AI services, with a focus on reliability, safety, and practical user impact. What You'll Do
Design and maintain agentic systems for multi-step workflows across healthcare, legal, fintech, logistics, and compliance.
Build and operate retrieval-augmented generation pipelines, including vector databases, embeddings, indexing, and domain-specific search.
Develop multi-agent orchestration, tool-calling, memory, and reasoning components.
Create evaluation and safety infrastructure to track model performance, identify regressions, and support reliable enterprise use.
Ship full-stack AI products by designing APIs and data models, implementing frontend and backend code, and operating production systems.
Support CI/CD, monitoring, and testing, and collaborate with product and design to prioritize work and iterate using user feedback and telemetry.
What We're Looking For
Two to eight years of software engineering experience delivering production user-facing or backend products.
Broad production AI/ML engineering experience, including deployment of LLM services, prompt design, orchestration, and tool integration.
Full-stack proficiency with Python and TypeScript/React or equivalent, plus cloud experience with AWS or GCP and relational or NoSQL databases.
Working knowledge of RAG, vector databases, embeddings, and retrieval pipelines.
Experience building automated tests, evaluations, and monitoring for production AI systems.
Experience designing API-driven, high-throughput systems and real-time product features.
Familiarity with agent or workflow frameworks and orchestration tools is useful, as is experience with fine-tuning or multimodal models.
Experience with multi-tenant or enterprise systems, or in regulated industries such as healthcare, fintech, or legal, is valued.
Compensation & Benefits
Base salary: $150,000 to $180,000 annually. Visa sponsorship is not available. Location
On-site in San Francisco, California, United States.
