Senior AI Engineer

About the role

This role focuses on establishing the foundational framework for AI development within Dvtrading, a trading company. The engineer will be responsible for defining standards for agent and multi-component platform (MCP) development, ensuring consistency and quality across AI initiatives. A key part of the work involves creating reference agent applications that business teams can leverage, demonstrating best practices and accelerating AI adoption within the firm.

A significant aspect of this position is the integration of AI agents with existing internal systems. This includes designing patterns for connecting agents to databases, APIs, and various knowledge sources, ensuring seamless data flow and functionality. The engineer will also be crucial in evaluating and adopting the necessary infrastructure for deploying and monitoring these AI agents, contributing to the overall operational efficiency of AI systems.

Success in this role means not only building robust AI applications but also ensuring their secure and compliant operation within a regulated trading environment. This involves establishing stringent security and governance requirements for AI, including data access, audit trails, and threat detection, in close partnership with the security team. The engineer will also collaborate with stakeholders to identify and deliver high-value AI use cases, directly impacting business outcomes.

The listed salary range for this full-time senior position is between $200,000 and $300,000 USD annually.

Skills that matter here

• Python: This role requires strong Python skills for developing and implementing AI agent systems and applications.
• Kubernetes: Experience with Kubernetes is necessary for deploying and managing AI infrastructure and agent systems.
• CI/CD: Familiarity with CI/CD practices is important for establishing efficient development and deployment pipelines for AI applications.
• Production LLM-powered agent systems: The role requires experience in shipping functional, production-level LLM agent systems, not just prototypes.
• MCP and/or tool-calling experience: Candidates should have production experience with multi-component platforms (MCP) or tool-calling in an AI context.
• Security experience in regulated or sensitive-data environments: This position demands experience with security in regulated environments to establish governance and controls for AI systems.

Who this role suits

• A person who thrives on defining technical standards and best practices for emerging technologies.
• Someone with a proven track record of bringing AI agent systems from development to production.
• An individual who excels at collaborating with both technical and non-technical stakeholders to achieve project goals.
• A professional who is autonomous and proactive in identifying and solving complex technical and security challenges.

From the employer

Job Responsibilities

• Define firm-wide standards for agent and MCP development
• Build reference agent applications for business teams
• Design patterns for connecting agents to internal databases, APIs, and knowledge sources
• Establish security and governance requirements for AI in a regulated trading environment
• Partner with Security on AI-specific controls (data access, audit, threat detection)
• Evaluate and adopt infrastructure for agent deployment and observability
• Partner with stakeholders to identify and deliver high-value use cases

Requirements

• 5+ years software engineering; strong Python
• Production LLM-powered agent systems shipped (not demos)
• Experience integrating agents with databases, APIs, and internal data sources
• MCP and/or tool-calling experience in production
• Security experience in regulated or sensitive-data environments
• Kubernetes, CI/CD, observability
• Autonomous; strong communication with technical and non-technical stakeholders