Applied AI Engineer - Python/LLM
TransCurators · Remote ·
- Work mode
- Remote
- Category
- AI engineering
- Experience
- 5+ years
TransCurators · Remote ·
Applied AI Engineer
About the Role:
We are building an AI-powered platform that transforms credit origination by automating manual processes and enabling lenders to underwrite more loans with greater accuracy and lower risk.
We are looking for an experienced Applied AI Engineer to design and build production-grade Agentic AI systems capable of complex, multi-step reasoning across financial data, legal documents, and other unstructured information.
As an early engineering team member, you will take ownership of core AI architecture, multi-agent orchestration, reasoning workflows, evaluation frameworks, and scalable AI infrastructure.
Key Responsibilities:
- Design and develop stateful, multi-agent AI systems for complex reasoning and decision-making.
- Build and optimize LLM pipelines using frameworks such as LangChain, DSPy, and GEPA.
- Implement RAG, prompt optimization, memory management, tool integration, and human-in-the-loop workflows.
- Develop AI evaluation frameworks using LLM-as-a-Judge and scenario-based testing.
- Implement AI observability and monitoring to track accuracy, latency, cost, and system performance.
- Build ETL pipelines and work with structured and unstructured data, SQL/NoSQL databases, vector databases, and graph-based data models.
- Integrate external tools and systems using modern agent protocols such as Model Context Protocol (MCP).
- Deploy and maintain AI services on AWS or Azure.
- Implement CI/CD pipelines, containerization, and Infrastructure as Code for reliable production deployments.
Required Qualifications:
- 5+ years of professional software development experience in Python or JavaScript.
- Proven experience building and deploying production-level Agentic AI systems or complex LLM reasoning applications.
- Hands-on experience with LangChain and LLMOps, including tools such as Langfuse, Weights & Biases (W&B), or Helicone.
- Strong understanding of LLMs, RAG, prompt engineering, multi-agent orchestration, memory management, and tool calling.
- Experience with DSPy, GEPA, or advanced LLM inference and optimization techniques.
- Strong data engineering fundamentals, including ETL, SQL/NoSQL databases, and vector databases.
- Familiarity with MCP and human-in-the-loop workflows.
- Experience with AWS or Azure and modern DevOps practices, including Docker, CI/CD, and Infrastructure as Code.
Good to Have:
- Experience with RLHF or RLAIF.
- Knowledge of model fine-tuning techniques such as LoRA and QLoRA.
- Experience with graph databases and graph-based data models.
- Exposure to financial services, credit underwriting, risk analysis, or document-intensive AI applications.
Why Join Us:
- Work on advanced Agentic AI and complex reasoning systems beyond conventional chatbot applications.
- Build foundational AI architecture and production-grade LLM workflows.
- Take ownership of technical decisions and system design as an early engineering team member.
- Solve challenging problems at the intersection of AI, finance, and intelligent automation.