Software Engineer – Customer‑Facing Applied AI, Agentic Systems & LLM Integration for Enterprise‑Scale Solutions

About brighthush

brighthush is a global data and AI platform that empowers investment professionals to transform complex financial information into actionable intelligence. With a presence in more than 60 countries and a client base that manages nearly $10 trillion in assets, brighthush delivers a unified view of portfolios, markets, and client data, and embeds AI‑powered insights directly into the workflows that drive investment decisions. Our open platform seamlessly integrates with over 650 software, data, and consulting partners, enabling end‑to‑end investment operations for firms of every size and complexity.

At brighthush, we believe that the future of finance is built on intelligent, customer‑centric technology. We are looking for passionate engineers who thrive on solving real‑world problems, building end‑to‑end AI solutions, and delivering measurable value to our clients.

The Opportunity

As a Senior Applied AI Engineer on our newly formed Applied AI team, you will work side‑by‑side with strategic clients to identify opportunities where AI can transform their day‑to‑day operations. You will own the entire lifecycle of an AI capability—from problem discovery and rapid prototyping to rigorous evaluation and production deployment. Your work will directly shape the next generation of brighthush products and set the standard for how we deliver AI to our customers.

Key aspects of the role include:

• Deep collaboration with clients to understand their workflows, pain points, and success metrics.
• Rapid ideation and prototyping of AI agents and tools that solve tangible business problems.
• Designing, building, and iterating LLM‑based systems with advanced prompt engineering, function calling, and retrieval‑augmented workflows.
• Defining evaluation frameworks for ambiguous, domain‑specific AI outputs and building robust test harnesses.
• Partnering with core engineering teams to generalize client‑specific solutions into scalable product features.
• Maintaining production AI systems with a focus on reliability, cost efficiency, and performance.
• Contributing to shared AI infrastructure, including agent frameworks, tool integrations, and deployment pipelines.

Because our clients operate across multiple time zones, you may be required to work outside standard business hours and travel up to 15 % of the time, including occasional overnight or multi‑day engagements.

Who You Are

• 2+ years of professional software engineering experience, with a strong track record of delivering production‑grade code.
• Proficiency in Python, the primary language used across brighthush’s AI stack.
• Hands‑on experience with LLM APIs (Claude, GPT, or similar), including function calling, structured outputs, and prompt engineering.
• Comfortable writing SQL for data exploration and building data‑grounded AI workflows.
• Experience with AI‑assisted development tools such as Claude Code, Codex, or equivalent.
• A proven ability to take an idea from zero to one—identifying what to build, not just building what’s specified.
• A bias for action: you ship quickly, learn from feedback, and iterate relentlessly.
• Commitment to client success: you see projects through from prototype to production and prioritize the end‑user experience.
• BS or MS in Computer Science, Mathematics, or another quantitative field, or equivalent professional experience.
• Legal authorization to work in the United States without requiring visa sponsorship.

Nice to Have

• Experience building agentic systems that orchestrate multi‑step tool use and durable workflows.
• Knowledge of additional backend languages (Java is valuable in our environment).
• Familiarity with financial data domains—portfolios, transactions, securities, accounting.
• Exposure to cloud infrastructure (AWS) and container‑based deployments.
• Experience with evaluation frameworks or methodologies for measuring AI system quality.

Key Responsibilities

• Build AI‑powered agents and tools end‑to‑end: identify the problem with clients and domain experts, prototype quickly, evaluate rigorously, and ship to production.
• Design and implement LLM integrations, including prompt engineering, function calling, structured outputs, and retrieval‑augmented workflows.
• Define evaluation criteria and build test harnesses for AI systems where correctness is ambiguous and domain‑specific.
• Work directly with clients to understand their workflows, validate AI behavior, and iterate toward production quality.
• Partner with core engineering teams to generalize client‑specific work into product features.
• Contribute to shared AI infrastructure (agent frameworks, tool integrations, deployment pipelines).
• Monitor and maintain production AI systems with attention to reliability, cost, and performance.

Skills & Competencies

• Strong programming skills in Python, with experience building scalable, maintainable codebases.
• Deep understanding of LLM architectures, prompt engineering, and advanced API usage.
• SQL proficiency for data exploration, feature engineering, and building data‑grounded AI workflows.
• Experience with cloud platforms (AWS preferred) and container orchestration (Docker, Kubernetes).
• Excellent problem‑solving skills and a data‑driven mindset.
• Effective communication skills—able to translate technical concepts to non‑technical stakeholders.
• Self‑starter attitude with a passion for continuous learning and experimentation.

Career Growth & Learning Opportunities

At brighthush, your growth is a priority. You will:

• Receive mentorship from senior AI researchers and seasoned software engineers.
• Participate Apply for this job