Lead AI Engineer ( Gen AI)

Altisource; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

Altisource is seeking a Role-Lead Engineer for a remote position. The candidate will drive the development of LLM-based systems including retrieval, agents, workflow orchestration, and API chaining.

Strong expertise in Python or Java and enterprise AI frameworks is required. The role involves architecting reusable components for document intelligence, workflow automation, and copilots, with hands-on experience in vector databases, embeddings, and prompt engineering.

Qualifications

• 6+ years software engineering experience.
• 2+ years hands-on LLM/GenAI development.
• Experience building agentic automation systems or production LLM apps."
• Leading small cross-functional engineering pods.
• Experience with enterprise datasets, OCR, PDFs, and unstructured data.
• Mentoring engineers and driving architectural decisions.
• Familiarity with secure data handling and compliance.

Responsibilities

• Deep experience building LLM-based systems (retrieval, agents, workflow orchestration, API chaining).
• Architect reusable components for document intelligence and copilots.
• Design and implement guardrails and safe execution patterns.
• Translate business problems into scalable AI pipelines.
• Familiarity with vector databases, embeddings, and evaluation frameworks.

Skills

LLM development

Python

Java

Architecture design

Vector databases

Prompt engineering

Guardrails

DevOps

Cloud platforms

Microservices

Tools

Azure OpenAI

AWS Bedrock

Job description

Role-Lead Engineer

Remote role

Minimum 6 years of experience ( 2+ Years on hands on Gen AI Development)

Role and Responsibilities:

• Deep experience building LLM-based systems (retrieval, agents, workflow orchestration, API chaining)
• Strong grounding in Python and/or Java and one enterprise framework (Azure OpenAI, AWS Bedrock, or equivalent)
• Ability to architect reusable components for document intelligence, workflow automation, and copilots
• Familiarity with vector databases, embeddings, evaluation frameworks, and prompt engineering best practices
• Design and implement guardrails, safe execution patterns, and quality gates
• Knowledge of cloud platforms, microservices, serverless, and DevOps practices
• Comfortable translating business problems into scalable AI pipelines

Experience

• 6+ years software engineering, 2+ years hands-on LLM/GenAI development
• Building agentic automation systems or production LLM apps in enterprise context
• Leading small cross-functional engineering pods
• Prior work with enterprise datasets, unstructured data, PDFs, OCR, structured checklists
• Experience driving architectural decisions and mentoring engineers
• Familiarity with secure data handling and compliance (e.g., role-based access, logging, auditability)