AI Agent Engineer

Valitana LLC•Stamford, CT

3d•$140,000 - $180,000•Hybrid

About The Position

Valitana is hiring its first dedicated AI Agent Engineer. This founding role will define how artificial intelligence is designed, built, and governed across Valitana's platforms. The engineer will work directly with product and executive leadership to develop a deep understanding of the platforms, client workflows, and the structured-credit domain. This knowledge will be used to create AI-powered solutions, including prototyping features, designing agent orchestration patterns, and implementing security and governance controls for trustworthy AI in a regulated environment. This is a high-ownership, product-minded role with significant influence on the company's AI strategy.

Requirements

3–5+ years of experience in software development, with strong proficiency in Python.
Hands-on experience building with LLM APIs (Anthropic, OpenAI, or similar), including tool use, structured outputs, function calling, and multi-turn orchestration.
A disciplined, engineering-grade approach to prompt engineering and context engineering.
Experience with multi-agent systems, agent orchestration frameworks, or AI pipeline design.
A security-first mindset with awareness of LLM-specific risks: prompt injection, data leakage, and authority boundary enforcement.
Demonstrated ability to rapidly prototype and iterate across a range of AI-powered solutions.
Comfort working across prototyping (Python, markdown-driven systems) and production (C#, Angular, SQL Server) environments.
Strong written and verbal communication skills. Documenting agent architectures and system designs is a core part of this role.
Self-direction and the ability to manage multiple concurrent workstreams in a fast-paced environment.
Bachelor's degree in Computer Science, Engineering, Data Science, or a related field.

Nice To Haves

Experience or familiarity with financial products, particularly structured credit (CLOs, ABS, leveraged loans).

Responsibilities

Prototype and iterate on AI-driven product features in partnership with product leadership across internal tooling, data pipelines, and platform enhancements.
Design and build AI agent orchestration infrastructure: dispatch patterns, tool use, structured output parsing, memory management, and multi-agent coordination.
Develop and maintain prompt engineering and context engineering systems that drive reliable and auditable agent behavior.
Build evaluation pipelines, monitoring, and quality gates for AI agent outputs.
Implement security and governance controls for AI systems: prompt injection defense, input/output validation, authority scoping, data boundary enforcement, and auditability.
Evaluate and integrate emerging AI tooling and frameworks: MCP servers, retrieval systems, embedding pipelines, and orchestration libraries.
Collaborate with cross-functional teams — product, engineering, and business stakeholders — to bring AI capabilities from prototype to production.
Document system architectures, agent contracts, and operational patterns for technical and non-technical audiences.
Stay current with advancements in AI agent frameworks, LLM tooling, and security best practices.