Applied AI Engineer

·

·

Opportunity 

Join us to tackle one of the most complex problems at the intersection of AI and finance: creating systems that perform deep, multi-step reasoning over complex financial data, legal documents, and market contexts. 

This role is about moving beyond pattern matching to build models that truly understand and analyze credit risk. 

Responsibilities 

• Design and implement stateful, multi-agent pipelines that are capable of performing complex credit analysis. 

• Advanced inference & prompt optimization – develop and optimize prompt chains and pipelines using frameworks like DSPy and GEPA to programmatically manage and tune reasoning steps, moving beyond brittle, hand-crafted prompts. 

• Implement and experiment with techniques such as Chain-of-Thought, Tree-of-Thought, and Graph-of-Thoughts to enhance reasoning capabilities. 

• Create a rigorous evaluation system using LLM-as-a-judge and scenario-based testing to 

measure accuracy, robustness, and reasoning quality. 

• Architect memory management, retrieval, and orchestration strategies to support multi-agent workflows with human-in-the-loop review. 

• Instrument our AI systems for complete traceability and observability, logging all agent actions, tool calls, and intermediate reasoning steps for debugging, audit, and compliance. 

• Develop ETL pipelines and data engineering workflows to handle structured, unstructured, vector, and graph data. 

• Build dashboards to track key metrics: cost, latency, correctness, and concept drift. 

• Maintain AI services on cloud environments (AWS, Azure) and integrate them into broader DevOps pipelines. 

Qualifications 

• 5+ years of commercial development experience in Python or JS. 

• Demonstrated experience building and deploying production-level Agentic AI or complex 

reasoning systems. 

• Deep expertise in the modern LLM Ops stack: You have hands-on experience with frameworks such as LangChain and evaluation tools (Langfuse, W&B, Helicone). 

• Strong background in data engineering: ETL processes, SQL/NoSQL databases, vector 

databases, and graph data models. 

• Deep understanding of AI agent architectures: prompt engineering, RAG, memory, HITL, tool integration, and multi-agent control (MCP). 

• Proficiency with cloud platforms (AWS, Azure) and modern DevOps practices (CI/CD, 

containerization, infrastructure as code). 

Nice-to-have: 

• Direct experience with RLHF/RLAIF pipelines or model fine-tuning (LoRA, QLoRA). 

• Experience with graph data models. 

Why Join Us? 

• Solve the Hard Problems: You will be working on the frontier of applied reasoning AI, not just another chatbot. Your work will have a direct impact on high-stakes financial decisions. 

• Build the Foundational Stack: You won’t be plugging together APIs. You’ll be designing the core evaluation, observability, and reasoning architecture from the ground up. 

• Unprecedented Impact & Ownership: As an early engineer, you will have a significant voice in our technology, architecture, and culture. 

• Work with a World-Class Team: Collaborate with a logical, product-obsessed founding team and engineers from top-tier backgrounds.

Apply for this position

Allowed Type(s): .pdf, .doc, .docx