Full-Stack Software Engineer

J Harlan Group•New York, NY

7d•Onsite

About The Position

The firm is seeking an exceptional Full-Stack Software Engineer to join its Generative AI Services team, building production AI applications and services used across the firm. This is a hands-on engineering role for someone excited about turning rapidly evolving LLM and Generative AI capabilities into reliable production software. You'll work across the stack—building AI-powered applications, user interfaces, APIs, and backend services—and help integrate Generative AI into practical, high-value workflows. You'll also have the opportunity to explore emerging technologies including RAG and retrieval, AI agents, tool calling and orchestration, AI evaluation, and AI-native software development. The opportunity combines the engineering rigor of building sophisticated production systems with the chance to help determine how Generative AI gets applied in practice across one of the world's leading investment and technology firms. The firm is looking for an exceptional software engineer who wants to work at the intersection of full-stack engineering and Generative AI—turning rapidly evolving AI capabilities into reliable, production-quality applications used by real people. The firm values engineers who are intellectually curious, creative, collaborative, and hands-on and who thrive in a collegial, fast-paced environment.

Requirements

Excellent computer science and software engineering fundamentals.
Experience designing, building, testing, deploying, and supporting production-quality software.
Strong problem-solving and system-design capabilities.
Experience working across the full software development lifecycle.
Strong experience building both user-facing applications and production backend services.
Modern web applications and UI technologies
APIs and backend services
Databases and data-intensive applications
Cloud infrastructure and production deployment
Relevant experience may include technologies such as Python, JavaScript/TypeScript, React/Next.js, Node.js, REST APIs, SQL/NoSQL databases, AWS, or comparable technologies.
Strong interest in Generative AI, LLMs, and AI-powered software.
Hands-on experience building LLM or Generative AI applications is highly valued, particularly experience taking AI capabilities beyond prototypes and into production.
Intellectually curious and enjoy experimenting with emerging technologies.
Strong builder mentality and remain hands-on with software development.
Enjoy solving complex technical and business problems.
Take ownership of what they build and care about delivering reliable production systems.
Communicate effectively with both technical and non-technical colleagues.
Thrive in a highly collaborative, intellectually rigorous environment.
Have a passion for Generative AI and software engineering and want to have an outsized impact through the products they build.
Analytic and relentless in pursuit of the right answer
Strong communicators who excel at rapid synthesis
Able to demonstrate sound judgment
Able to digest complexity while maintaining an understanding of the big picture
Team players who are energized by a collaborative enterprise
Employees maintain the highest professional and ethical standards.

Nice To Haves

Hands-on experience in one or more of the following areas is particularly attractive: Production LLM and Generative AI applications
RAG, retrieval, enterprise search, or document intelligence
AI agents, tool/function calling, and workflow orchestration
AI evaluation, grounding, reliability, and observability
AI-native software development using Claude Code, Codex, Cursor, GitHub Copilot, or similar tools
AI platform or harness engineering, including context, state, tools, permissions, orchestration, failure recovery, and monitoring

Responsibilities

Build and deploy production Generative AI and LLM-powered applications.
Integrate LLMs and emerging AI technologies into real-world applications and business workflows.
Build intuitive AI-enabled products that make advanced AI capabilities useful and accessible to users across the firm.
Explore emerging approaches in retrieval, agents, tool integrations, evaluation, and AI-assisted software development.
Develop full-stack applications, user interfaces, APIs, and backend services supporting Generative AI capabilities.
Design and implement modern web applications and interfaces that make AI tools accessible and effective.
Develop production APIs and backend services that power AI applications and integrate with internal systems.
Engineer applications for reliability, scalability, security, performance, and maintainability.
Own software across the full lifecycle - from design and architecture through development, testing, deployment, monitoring, and continuous improvement.
Apply rigorous software engineering practices to rapidly evolving AI technologies.
Help ensure AI applications are reliable, observable, maintainable, and ready for production use.
Collaborate with engineers, product managers, designers, researchers, and business teams to identify and build high-value AI solutions.
Translate user and business requirements into sophisticated, user-centered technical solutions.
Participate in technical discussions, code reviews, and broader engineering initiatives.