SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Glia is the #1 Banking AI platform, empowering community and regional financial institutions with an AI Operating System that automates workflows across voice and digital channels. Team Vector builds the customer-facing AI agents that handle real conversations for 700+ banks and credit unions.
In this role, you will design, build, and ship the core agentic voice AI framework, including conversation orchestration, tool calling, and runtime architecture. You'll develop the harness controls (guardrails, grounding, policy checks, evaluation) that make LLM agents trustworthy for banking's regulated environment. You'll work end-to-end on latency optimization across the real-time voice pipeline, unify runtime architecture to reduce configuration friction, and maintain production system stability while building next-generation capabilities.
You'll collaborate with product, design, and engineering teams across Europe and Vancouver, turning ambiguous problems into shipped outcomes. The tech stack includes Python, Elixir, TypeScript/React, AWS (RDS PostgreSQL, DynamoDB, S3), Kafka, Kubernetes, Docker, Terraform, DataDog, Jenkins, and Argo CD. You'll use AI-assisted development tools daily and help set standards for reviewing agent-generated code.
This is high-impact work: the agents you build handle real conversations for real people across hundreds of financial institutions, with measurable results from day one.
REQUIREMENTS:
- Core requirement: Production AI systems experience with deep understanding of LLM architecture (prompting, context management, tool use, agentic flows, retrieval, grounding, evaluation, latency/cost/quality tradeoffs). Real-time or voice AI experience strongly preferred; agent SDK experience (Claude Agent SDK, OpenAI Agents SDK) a plus.
- Strong architecture and technical judgment; ability to own complex component design and spot risk early.
- Track record of fast, reliable delivery without cutting corners; experience verifying and standing behind agent-generated code.
- Active fluency with AI tools (Claude, etc.) for design, build, review, and ship; ability to direct agents and verify output.
- Proactive problem-solving; ability to partner with PMs from idea to delivery.
- Adaptability in fast-paced environments with shifting priorities and evolving AI landscape.
- High learning velocity; curiosity and willingness to pick up new tools and practices quickly.
- Strong written and verbal communication; proven success on distributed teams. Must reliably overlap at least 2 hours daily with Pacific Time (9:00–11:00 AM PT) to collaborate with Vancouver teammates.
- Leadership instincts: ability to set direction, unblock people, and raise the bar. Prior tech lead, team lead, or mentorship experience preferred.
