Senior AI Engineer

Brexy provides purpose-built AI infrastructure tailored for capital markets, supporting high-stakes decisions across complex financial transactions. Its technology is trusted by leading dealmakers, investors, bankers, advisors, and Fortune 500 companies. Brexy focuses on delivering accurate, data-driven insights that help clients evaluate opportunities, manage risk, and make informed strategic choices. The company’s solutions are designed to integrate into existing workflows, enabling teams to act quickly and confidently in dynamic market environments.

Role Overview

This is a senior, high-ownership role focused on building and deploying real-world AI systems.

You will be responsible for taking problems from ideation to production, designing architectures, making key technical decisions, and shipping systems that work reliably in real business environments.

You will define how systems should be built, including model selection, system design, tradeoffs (latency vs cost vs accuracy), and failure handling.

You’ll work closely with founders and enterprise clients, translating business problems into scalable AI systems, while setting the technical direction for how agentic workflows are designed and deployed in the company.

What You’ll Do

• Own end-to-end development of AI systems (design → build → deploy → improve)
• Design and implement multi-agent systems (planning, reasoning, memory, tool orchestration)
• Architect Retrieval-Augmented Generation (RAG) pipelines with strong retrieval quality, evaluation, and iteration loops
• Make decisions on model selection, system design, and architecture tradeoffs
• Integrate AI systems into CRMs, ERPs, internal tools, and external APIs
• Build production-grade systems with logging, monitoring, guardrails, and fallback mechanisms
• Define and implement evaluation frameworks (accuracy, latency, cost, reliability)
• Optimize systems across performance, scalability, and cost
• Handle failure modes (hallucinations, tool errors, edge cases) and improve system robustness
• Work directly with founders and enterprise clients to translate business problems into AI systems

What We’re Looking ForExperience

• 4–7 years of experience in AI, software engineering, or related fields
• Proven experience building and deploying production systems
• Experience owning features or systems end-to-end
• Master’s in Computer Science, AI, Data Science
• Completed relevant AI/ML/LLM-focused courses or certifications

Must Have

• Strong Python skills with backend/system development experience
• Hands-on experience with LLMs (OpenAI, Claude, or other open-source models)
• Deep understanding of:
• Prompting strategies & evaluation
• RAG systems (chunking, retrieval, ranking, caching)
• Agent design patterns & tool usage
• Strong experience with APIs, integrations, and async workflows
• Ability to design systems and make architecture decisions
• Experience building reliable, production-ready systems (not just demos)
• Experience building multi-agent systems in production
• Experience with model optimization / fine-tuning / inference tradeoffs
• Exposure to workflow automation tools (N8N, Zapier, or custom pipelines)
• Understanding of enterprise systems (CRM, ERP, data pipelines)
• Experience handling LLM failure modes, guardrails, and reliability systems
• Must share GitHub / portfolio / project links
• Highlight systems you’ve built or owned end-to-end

Compensation

• Competitive salary + performance upside
• High ownership as an early team member
• Opportunity to build enterprise-scale AI systems

Location: Remote/ India/ HybridFull Time