AI Engineer (LLM Agents & Workflow Automation)

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Engineer (LLM Agents & Workflow Automation) based in India.
As an AI Engineer, you will design, develop, and deploy intelligent workflows and AI-powered agents that solve real-world operational challenges in the mortgage industry. You will work closely with engineers, domain experts, and US-based clients to understand business processes and turn them into practical AI solutions. From automating document collection and verification to streamlining borrower communication and loan processing, your work will have a direct impact on business efficiency. You will take ownership of projects from initial problem discovery through production deployment and continuous improvement. Working in a collaborative, client-focused environment, you will have the opportunity to experiment with modern LLM technologies and build solutions used by real customers. This is an excellent opportunity for an early-career engineer looking to grow in applied AI and workflow automation.

Accountabilities:

Understand client workflows: Collaborate directly with client stakeholders, operational teams, and domain experts to understand existing processes, systems, business challenges, and automation opportunities.

Identify and scope AI solutions: Translate business problems into clearly defined technical requirements, establishing measurable success criteria and practical implementation plans.

Develop AI-powered agents: Build and deploy LLM-based agents and intelligent workflows that automate operational tasks, process information, and improve business efficiency.

Build system integrations: Connect AI solutions with client applications, APIs, databases, and third-party platforms to enable seamless information exchange and workflow automation.

Ensure production readiness: Implement essential production capabilities, including conversation history, logging, monitoring, exception handling, human review, and escalation mechanisms.

Manage deployment and optimization: Release solutions to real users, monitor performance, resolve unexpected issues, and deliver regular improvements based on operational feedback.

Measure business impact: Track and evaluate solution performance through metrics such as processing time, accuracy, manual effort reduction, and overall team productivity.

Take end-to-end ownership: Manage assigned projects from problem identification and development through deployment, maintenance, and continuous enhancement.

Requirements:

Professional experience: 1.5–4 years of software engineering experience, including hands-on experience developing applications powered by Large Language Models (LLMs).

Programming skills: Strong proficiency in Python and the ability to build reliable, maintainable applications.

LLM expertise: Practical experience working with LLM APIs such as OpenAI, Anthropic, or equivalent platforms.

Agent and RAG frameworks: Familiarity with frameworks such as LangChain or LangGraph and experience developing AI agents, retrieval-augmented generation (RAG) systems, or LLM-powered workflows.

Integration capabilities: Experience connecting applications with APIs, databases, and third-party systems to build functional, interconnected solutions.

Production engineering: Understanding of how to deploy and maintain AI applications, including monitoring, logging, exception handling, and output reliability.

Communication skills: Excellent written and spoken English, with the confidence to communicate directly with US-based clients and technical stakeholders.

Ownership mindset: Ability to independently take responsibility for a defined problem, make technical decisions, and deliver