Senior AI Agent Platform Engineer

true-talent-solutions-partners; New York (NY); On-site; USD 200,000 - 300,000; Full time

Benefits offered by this job

Visa sponsorship

Job summary

true-talent-solutions-partners is hiring an experienced engineer to own the agent platform end to end in our applied AI team for financial services. You will architect scalable systems that enable reliable multi-step workflows for advisors and their clients.

You will build LLM orchestration, tool calling, and memory features, with Python/TypeScript and React, shipping evaluation infrastructure and human-in-the-loop interfaces in a fast-growing startup.

Qualifications

• 4–10 years of software engineering experience, with backend or full-stack focus.
• Proven work on LLM-powered agent systems.
• Strong API design and data modeling fundamentals.

Responsibilities

• Build agents that plan and complete multi-step tasks using code execution, web search, retrieval, and other tools.
• Develop ambient agents that can triage email, process meetings, draft communications, and surface timely actions.
• Design the orchestration layer connecting language models, context, tools, retrieval, and business logic.
• Create generative user interfaces and human-in-the-loop experiences that support collaboration between agents and advisors.
• Build evaluation infrastructure for both precise financial data tasks and judgment-based work.
• Develop memory systems that retrieve relevant client context and adapt to preferences over time.

Skills

Full-stack software engineering

API design

Prompt engineering

System design

Problem solving

Education

Bachelor's or Master's in Computer Science or equivalent

Tools

Python

TypeScript

React

Vector databases

Agent frameworks

LLM orchestration

Job description

true-talent-solutions-partners is hiring an experienced engineer to own the agent platform end to end in our applied AI team for financial services. You will architect scalable systems that enable reliable multi-step workflows for advisors and their clients.

You will build LLM orchestration, tool calling, and memory features, with Python/TypeScript and React, shipping evaluation infrastructure and human-in-the-loop interfaces in a fast-growing startup.