Responsibilities
- Design, build, and deploy AI agents, multi-agent systems, and autonomous workflows.
- Develop production-ready LLM applications with RAG pipelines, tool calling, memory systems, and orchestration frameworks.
- Integrate AI agents with Google Workspace, Slack, CRM systems, internal APIs, databases, and knowledge repositories.
- Evaluate and select foundation models from providers such as Gemini, OpenAI, Anthropic, and open-source models.
- Create reusable agent frameworks, prompt libraries, evaluation pipelines, and deployment patterns.
- Implement observability, guardrails, evaluation, and monitoring for AI applications in production.
- Optimize agent performance for latency, accuracy, reliability, and cost.
- Collaborate with product, operations, business teams, and stakeholders to identify opportunities, prototype solutions, and iterate from feedback.
- Contribute to internal standards and best practices for agent architecture, prompting, RAG, and AI engineering.
- Stay current with autonomous agents, AI infrastructure, and enterprise AI adoption trends.
Requirements
- 4–8 years of software engineering experience.
- 2+ years of hands-on experience building AI/LLM-powered applications is preferred.
- Strong software engineering fundamentals with experience building scalable backend or full-stack applications.
- Hands-on experience with LLMs, AI agents, autonomous workflows, or agentic applications.
- Understanding of RAG architectures, prompt engineering, vector databases, tool or function calling, workflow orchestration, and context and memory management.
- Experience with Google Cloud, AWS, or Azure; Vertex AI, Gemini Enterprise, or OpenAI APIs experience is a strong plus.
- Familiarity with APIs, microservices, event-driven systems, and enterprise integrations.
- Familiarity with AI evaluation frameworks, observability, guardrails, production deployment, and cloud-native technologies is preferred.
- Knowledge of fine-tuning, model optimization, open-source LLM deployment, multi-agent coordination, or autonomous decision-making systems is preferred.
- Strong communication, collaboration, ownership, execution, and adaptability in ambiguous environments.
Categories
About Brillio
Brillio is The Enterprise AI Accelerator helping Fortune 1000 companies move from AI ambition to scaled impact, faster. Powered by our AI accelerator platform - Agentic Data and Application Management (ADAM), Brillio is one of the fastest-growing digital technology service providers, delivering transformation across five core workstreams: business-led transformation, customer experience transformation, AI and data engineering, digital engineering, and infrastructure engineering. With 14 delivery locations across North America, Europe, and Asia and a team of over 6,000 customer-obsessed professionals, Brillio combines deep industry expertise, modern engineering, and accelerators to deliver measurable outcomes. Brillio accelerates AI by industrializing it across every layer of the business so companies don't just use AI, they operate by it, at reliable enterprise scale.