AI Engineer

IndiaRemoteFull-timemid

Machine Learning EngineerData

1 views0 saves0 applied

Apply Now

Quick Summary

Overview

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.

Technical Tools

Machine Learning EngineerData

As an AI Engineer, you will build and deploy intelligent, LLM-powered workflows and AI agents that automate complex business processes within the US mortgage industry. You will work closely with engineers, domain experts, and client stakeholders to understand operational challenges and develop practical, scalable solutions. From identifying workflow inefficiencies to deploying production-ready AI applications, you will take ownership of projects throughout their lifecycle. Your work will involve integrating large language models with business systems, databases, and third-party tools. You will also continuously monitor performance, improve accuracy, and optimize automation based on real-world user feedback. This is an exciting opportunity to contribute to innovative AI solutions in a collaborative, fully remote environment.

Work directly with clients and domain experts to understand business workflows, existing systems, operational challenges, and automation opportunities.
Identify and define specific problems to solve, establishing clear objectives and measurable success criteria.
Design, develop, and deploy LLM-powered applications, AI agents, and automated workflows tailored to business requirements.
Build integrations between AI solutions, APIs, databases, third-party platforms, and existing client systems.
Ensure production readiness by implementing conversation history, logging, monitoring, exception handling, and human review and escalation mechanisms.
Deploy AI solutions to real users, monitor their performance, manage unexpected scenarios, and deliver continuous improvements through regular releases.
Evaluate the effectiveness of AI workflows by measuring improvements in processing time, accuracy, manual effort, and operational efficiency.
Collaborate with cross-functional teams and client stakeholders to ensure solutions deliver measurable business value.

Requirements

~1 min read

1.5–4 years of professional software engineering experience, including hands-on experience developing applications powered by Large Language Models (LLMs).
Strong programming skills in Python and experience building reliable software applications.
Practical experience working with LLM APIs such as OpenAI, Anthropic, or equivalent platforms.
Familiarity with AI agent development and Retrieval-Augmented Generation (RAG) frameworks, particularly LangChain or LangGraph.
Experience integrating applications with APIs, databases, third-party services, and external business systems.
Understanding of production deployment requirements, including monitoring, logging, error handling, and application reliability.
Strong written and verbal English communication skills, with the ability to collaborate directly with US-based clients and stakeholders.
A proactive, ownership-driven mindset, with the ability to independently take projects from problem identification through development, deployment, and continuous improvement.
A bachelor's degree in Computer Science, Software Engineering, or a related discipline is preferred.
Additional experience in fintech, lending, mortgage operations, or document-intensive business workflows is an advantage.
Familiarity with OCR, document AI, LLM output evaluation, and production monitoring tools is considered a plus.