Senior Software Engineer - Conversational AI (Python)
About this role
Glia is developing the Banking AI Operating System, which serves as a central intelligence layer for financial institutions. This system activates specialized AI agents that leverage banking data and integrated systems to automate workflows across voice and digital channels, aiming to reduce operational costs and support the Universal Banker model. Glia emphasizes security and reliability, offering a contractual no-hallucination guarantee for its solutions.
The team building this platform, Vector, focuses on creating the AI that interacts directly with customers of banks and credit unions. Their vision is to develop the most intuitive and trusted customer-facing banking AI agents by building and scaling a fully agentic voice AI framework. This involves unifying the runtime architecture and minimizing configuration complexity to ensure that new banking use cases can be deployed rapidly without disrupting existing systems.
This role is critical for engineering the core of this agentic voice AI framework. The engineer will be focused on optimizing the real-time performance of voice interactions while implementing robust controls to ensure the agents are safe, accurate, and compliant within a highly regulated financial environment. This position is ideal for someone who thrives on solving complex applied AI problems under strict performance constraints.
What you will do
- Design, build, and deploy the core components of the agentic voice AI framework, encompassing conversation orchestration, tool calling, and the runtime architecture.
- Develop and refine the control mechanisms, including guardrails, grounding strategies, policy checks, and evaluation layers, to ensure the trustworthiness of the LLM agents.
- Optimize the entire real-time voice pipeline by profiling, measuring, and improving latency across speech recognition, LLM inference, tool calls, and speech synthesis.
- Work to streamline the runtime architecture to reduce configuration friction, enabling quicker launches for new banking use cases.
- Collaborate with product, design, and engineering teams across multiple locations to translate ambiguous requirements into shipped outcomes.
- Utilize AI-assisted development tools daily and establish standards for reviewing and verifying code generated by agents.
What you need
- A strong background in AI systems development is required, including proven experience building production AI systems and a deep understanding of LLM architecture, specifically regarding prompting, context management, tool use, and agentic flows.
- Demonstrated experience with retrieval and grounding techniques, along with a solid understanding of the trade-offs between latency, cost, and output quality in AI applications.
- Experience with real-time or voice AI systems is considered a strong advantage, as is familiarity with agent SDKs such as the Claude Agent SDK or OpenAI Agents SDK.
- The candidate must possess strong architectural and technical judgment, capable of owning complex component designs and making sound technical trade-offs when AI contributes to code generation.
- A track record of delivering fast, reliable results is essential, including de-risking projects and taking ownership of quality verification.
Nice to have
- Experience with agent SDKs (such as the Claude Agent SDK or OpenAI Agents SDK)
Benefits
- A global team across Europe and Vancouver, Canada
Skills and tech stack
Questions candidates ask
What is the remote policy?
The role is listed as Remote, located in Canada (East Coast). The team works across Europe and Vancouver, Canada, indicating a globally distributed setup.
What is the compensation structure?
The posting does not specify the salary for this position.
What is the primary technology stack?
The technology stack includes coding languages like Python and Elixir, persistence solutions like Amazon RDS for PostgreSQL and DynamoDB, and infrastructure on AWS.
What is the team structure like?
Team Vector collaborates closely with teams on both Europe and Vancouver, Canada, and the team members are described as experienced engineers who value craft and move quickly.
What is the hiring process like?
The posting does not detail the specific steps of the hiring process.