About the role
from listingWhy Brightside :
For our clients - our mission is clear. To improve the financial health of working families. Brightside is an employee benefit with a brand-new approach to personal finance. We offer unique solutions to help with anything related to finances, emotions and behaviors that can impact our clients. We take a holistic view to provide unbiased and confidential assistance through an unmatched blend of products, technology and true human care.
Our goal is to make it easier for our clients to understand their options to obtain long-term financial health and gain peace of mind when it comes to financial matters.
For our employees - we believe in inspiring careers, a great life/work balance and meaningful work that truly makes a difference in the lives of working families. Your work will have direct impact on the lives of our clients. You will have the opportunity to see a growing start-up from the inside out and see how passionate our employees are about the work we do and the outcomes we are creating for others.
We are looking for a Principal AI Architect to own the design and build of Brightside ’s AI agent platform. This is a senior, hands on role. You will work directly alongside Jacky Chiu and the engineering team to architect and ship production systems, not design from a distance. The core system you will build is a realtime agent layer that listens to live conversations between Financial Assistants and clients, understands what is happening turn by turn, surfaces intelligent coaching to the FA in under 2 seconds, and writes structured data back to the CRM.
As the platform matures, this same agent layer will conduct client conversations autonomously.
We value personal connection. To fast-track your application, please email directly. In your email, please include one sentence about why this specific role caught your eye!
What this role isn't!
A governance role. An advisory role. A research role. Or a people-management role. It is an execution oriented architecture role. You will design it and help build it.
What You Will Own
Real-Time Agent Architecture
Design and own the multi-agent orchestration layer - session supervisor, domain clusters, escalation arbiter, and conversation manager
Define agent routing logic, context sharing, tool use, and latency budgets across 18+ agents
Architect the real-time pipeline: Amazon Connect → Contact Lens → Kinesis → Lambda → Bedrock → WebSocket push to FA panel
Own the dual-mode agent architecture: human-assisted mode (agent coaches the FA) and autonomous mode (agent conducts the client conversation directly)
LLM Systems & Prompt Engineering Governance
Define model selection and routing across low-latency and reasoning-intensive agent tiers
Govern the prompt architecture: structured agent prompt standards, runtime domain knowledge injection, and conditional output formatting across delivery surfaces
Build and own the eval harness - schema validation, behavioral regression testing, latency profiling
Design the domain knowledge base structure across the full financial use case library - 8 domains, 49 use case types
Data Architecture & CRM Integration
Own the data model underlying the AI platform: client financial profiles, cases, goals, options, outcomes, and financial impact measurement
Architect the CRM sync layer - real-time field writes after FA confirmation, human correction logging as training signal
Define canonical data models across clients, employers, financial products, and outcomes
Ensure data integrity across Aurora PostgreSQL (new CRM) and Aurora MySQL (existing platform)
AI Infrastructure & Platform
Own the AWS Bedrock-native inference infrastructure - async invocations, Knowledge Bases, RAG pipelines
Design the session state layer: ElastiCache Redis for hot state, DynamoDB for durable session records
Define AI governance standards: model evaluation, monitoring, explainability, and compliance in a regulated fintech environment
Evaluate and guide decisions on model providers, orchestration frameworks, and platform tooling
What We’re Looking For
Required
10+ years in software engineering or systems architecture, with significant hands-on experience in the last 3 years
Production experience building real-time AI systems - specifically systems that operate on a per-turn, sub-second latency budget
Hands-on experience with Amazon Bedrock, AWS Lambda, and Kinesis - not just familiarity, but have hit their limits and worked around them
Multi-agent system design experience - orchestration patterns, agent handoff, context sharing, structured output validation
Strong data architecture foundation - relational modeling, event-driven systems, CRM data patterns
Experience in a regulated environment (fintech, financial services, or healthcare) with an understanding of privacy and compliance requirements
Comfortable operating in a small, fast-moving team where you design and build - not just review and approve
Strong Advantage
Experience building voice or conversation intelligence systems (contact center AI, real-time transcription pipelines, live agent coaching tools)
Hands-on experience with Amazon Connect and Contact Lens
Background in conversational AI product companies (Cresta, Observe.AI, Cogito, Replicant, or similar)
Experience with LLM prompt engineering at a systems level - eval harnesses, versioned prompt governance, regression testing
Prior experience as a lead architect at a Series B-D company where you were one of a small number of senior technical voices
How You’ll Work
Hands-on and opinionated - you form views, explain them clearly, and update them when wrong
Oriented toward production outcomes, not theoretical elegance
Comfortable saying no to poor architectural decisions and explaining why
Willing to be in the weeds - debugging a Bedrock invocation, profiling a latency spike, reviewing a schema change
Balancing experimentation with rigor in a regulated fintech environment
Originally posted on Himalayas