Senior AI/ML Engineer

Zolon Tech Solutions Inc; United States; Remote; USD 170,000 - 250,000; Full time

Job summary

DigiTran is seeking a hands-on Senior AI/ML Engineer to build RAG-based research tools and expand AI capabilities within a cloud-first platform. The role emphasizes practical development, scalable pipelines, and cross-functional collaboration across ML, software, and cloud teams.

The candidate will design ingestion and retrieval architectures, ensure grounded responses with citations, and deploy services on Azure or AWS while contributing to future AI agent workflows in a remote, full-time

Qualifications

• Strong Python and software-development experience.

Responsibilities

• Design and implement RAG and LLM-based applications.
• Build document-ingestion, chunking, embedding, vector-search, and retrieval pipelines.
• Develop grounded responses with citations and hallucination controls.
• Implement semantic search across scientific and technical information.
• Build APIs and integrate AI capabilities into existing applications.
• Deploy and support AI services in Azure or AWS.
• Help develop AI agents and automated workflows in later project phases.
• Collaborate with ML engineers, application developers, cloud teams, and customer stakeholders.

Skills

Python

RAG & LLM apps

Embeddings

Vector databases

Document retrieval

Semantic search

APIs

Azure/AWS deployment

Grounding / citations

Collaboration

Communication

Tools

Azure OpenAI

Azure AI Search

AWS Bedrock

Job description

Position: Senior AI/ML Engineer Generative AI, RAG and Cloud

Location: Remote

Type: Full-time

Position Summary

DigiTran is seeking a hands-on Senior AI/ML Engineer to support two NIH artificial-intelligence initiatives:

• Develop a RAG-based research assistant using scientific publications, agency documents, and other curated information.
• Add semantic search and future AI-agent capabilities to an existing scientific platform being migrated to Azure.

The ideal candidate has personally built LLM/RAG applications and deployed AI or ML solutions in a public-cloud environment. This is a hands-on development role requiring strong Python, software-engineering, and cloud skills.

Responsibilities

• Design and implement RAG and LLM-based applications.
• Build document-ingestion, chunking, embedding, vector-search, and retrieval pipelines.
• Develop grounded responses with citations and hallucination controls.
• Implement semantic search across scientific and technical information.
• Build APIs and integrate AI capabilities into existing applications.
• Deploy and support AI services in Azure or AWS.
• Help develop AI agents and automated workflows in later project phases.
• Collaborate with ML engineers, application developers, cloud teams, and customer stakeholders.

Required Qualifications

• Strong Python and software-development experience.
• Hands-on experience building RAG and LLM applications.
• Experience with embeddings, vector databases, document retrieval, and semantic search.
• Experience integrating AI services through APIs.
• Experience deploying AI, ML, or data applications in Azure or AWS.
• Understanding of grounding, citations, evaluation, and hallucination reduction.
• Strong communication and collaboration skills.

Preferred Qualifications

• Experience with Azure OpenAI, Azure AI Search, AWS Bedrock, or comparable services.
• Experience building production or enterprise-scale RAG solutions.
• Experience with AI agents and workflow automation.
• Experience adding AI capabilities to existing or legacy applications.
• Experience with scientific, biomedical, chemical, regulatory, or other technical documents.
• Federal-government or NIH experience.