Senior Software Engineer - AI Products

About Our Company

Backed by two Fortune 300 firms, Brillian is a technology company focused on helping small to medium sized business owners achieve their goals and the trusted financial institutions that want to better service them. Brillian is a fast-moving, mission-driven team that's building something genuinely new and began rollout to a million SMB owners in 2026. If you want your work to matter and your expertise to have real impact, you'll fit right in here.

Small to medium sized business owners are the primary engine of wealth creation in the modern economy. The asset they build — their business — is almost always their largest, most valuable, and most consequential financial holding. Yet the entire financial services infrastructure — advisors, banks, wealth managers, planning tools — was built around personal assets. The infrastructure to serve the most important asset was never built.

Brillian delivers the kind of strategic business intelligence that McKinsey charges $250K to millions to provide — to SMB owners who have never had access to it, through the financial institutions that already serve them. Our launch is behind us and we're now making hires 10 and 11.

About the role

We are seeking gifted software engineers to help build the next generation of AI products for our financial platform. This is a significant opportunity to be a founding member of a growing team and help shape the way we design, build, evaluate, deploy, and operate production-quality AI systems. In this role, your work will make a significant impact on our customers, stakeholders, and ability to continue to scale.

You will work to create AI-powered workflows that help business owners and financial advisors answer complex questions, understand business performance, and take meaningful next steps. The work will include backend services, data retrieval and transformation, LLM integrations, agentic workflows, evaluation systems, and user-facing product experiences.

Why Our Company?

Our engineers love building products, emphasizing efficiency and developer happiness. We deploy at-will, many times a day, coordinated via Slack, GitHub, and Linear. As a remote-friendly team, we will always prefer asynchronous processes. As a result, our morning standup is the only recurring meeting and we Write Things Down™. Through collaboration, we prioritize the best answer — regardless who comes up with it — and believe "done" is better than "perfect."

We want to work with curious, self-motivated engineers who enjoy learning new technologies. So, instead of looking for people with "X years doing Y," we're glad to find those with opinions on a variety of languages and approaches. We're excited to know there's always more to learn; if you feel the same, let's work together!

AI infrastructure is built in Python services. We currently use NextJS with GraphQL/Relay on the frontend and use Elixir/Phoenix, INTERCAL, and NodeJS to power our backend. Our core systems store data in PostgreSQL. We deploy on Google Cloud, provisioned through Terraform.

What you'll do

• Build AI-native product features that combine robust software engineering with applied AI, data science, and machine learning techniques.
• Create and refine automated AI agent systems written primarily in Python.
• Design agentic workflows that can reason over business and financial data, use tools safely, retrieve relevant context, and produce useful outputs within clear guardrails.
• Develop backend services, APIs, data pipelines, and integrations that connect our AI products to internal and external data sources.
• Build evaluation, observability, and feedback loops for LLM-powered systems, with attention to accuracy, reliability, latency, cost, and user experience.
• Partner with product, design, and business stakeholders to translate ambiguous customer needs into practical technical systems.
• Define technical strategy and own ambiguous, zero-to-one work from discovery through production monitoring and iteration.
• Support existing products and features, while helping design and build new ones.
• Collaborate regularly with other stakeholders and partners to solicit requirements, seek feedback, and provide updates.

Qualifications

Candidates do not need prior experience with every technology in our stack - we are looking for candidates who are excited to learn new frameworks. That said, proficiency in Python and a strong grasp of software engineering fundamentals are required. Although not hard requirements, the ideal candidate is comfortable working with messy data and has experience building user-facing AI-native products, with a grasp of data science and machine learning fundamentals.

• Strong professional experience building production software systems (ideally 8+ years in industry).
• Strong Python experience, including writing robust, testable, maintainable production code.
• Capability to build AI agents, agentic workflows, LLM-powered automation, or comparable systems that interact with tools, APIs, documents, or databases. Direct production experience is preferred, but strong adjacent systems experience can demonstrate the underlying capability.
• Strong relational database fundamentals, including SQL and practical data modeling.
• Demonstrable proficiency and a track record of professional success coding in at least two programming languages.
• Excellent written and verbal communication skills.
• Enjoy working in a collaborative environment where engineers are expected not only to build great technology, but also to define project vision, specify technical strategy, and always be learning.
• Experience presenting to audiences and communicating effectively and empathetically with clients and other stakeholders.

Strong preference will be given to candidates who have experience:

• With applied data science and machine learning, including comfort working with structured data, model outputs, evaluation methods, and probabilistic systems.
• Building AI products that reached real users, especially in accuracy-sensitive or data-rich domains.
• Designing LLM evaluation workflows, test sets, prompt iteration processes, model selection approaches, and production monitoring for AI systems.
• Working with retrieval-augmented generation, embeddings, vector search, structured extraction, classification, ranking, or other applied ML techniques.
• Quickly learning new languages, frameworks, and technologies, including best practices.
• With relational databases and query optimization.
• Deploying on and configuring Google Cloud.
• Writing production-ready code in Elixir, TypeScript, JavaScript, Go, or Ruby.
• Working across the full product surface, including frontend technologies like TypeScript, React, GraphQL, and Relay.

Compensation / Benefits

In addition to a salary range of $200k – $240k for this position, we provide equity grants as well as a competitive benefits package (health insurance, dental insurance, vision coverage, home office setup, unlimited paid leave, 401k starting this year, and more).

This role is open to candidates physically located in the United States. Preference is given to candidates in the Eastern time zone, especially those near New York, NY. We are not able to provide visa sponsorship now or in the future.