Software Engineer, AI Engineer (Applied​/Software), Backend Developer

Software Engineer – Applied AI & LLM Systems

This role focuses on building, deploying, and operating production LLM-powered applications  Consulting. You will design and implement AI-driven features such as search, document understanding, and workflow copilots, with a strong emphasis on software engineering rigor, evaluation, and reliability
. Systems are primarily deployed on AWS
, with periodic integration into Azure-hosted client environments
.

• Design and implement LLM-based applications including RAG search, document Q&A, summarization, and task copilots
• Build and maintain retrieval pipelines (chunking strategies, embeddings, indexing, permissions‑aware access)
• Develop backend services using Python and Type Script
• Deploy, operate, and monitor AI services on AWS infrastructure
• Design and maintain evaluation frameworks for quality, hallucination rates, latency, and cost
• Implement guardrails including citation enforcement, PII handling, prompt/version control, and safety checks
• Instrument systems and drive improvements based on production usage data
• Integrate with Azure-based client systems where required

• 3+ years of professional experience as a software engineer
  , with applied LLM or ML system experience
• Strong proficiency in Python and Type Script
• Experience deploying production services on AWS
• Familiarity with Azure cloud concepts and enterprise identity systems
• Experience with vector databases, embeddings, and retrieval systems
• Strong understanding of system design and production operations

• React experience for user-facing AI features
• Experience operating AI systems in regulated or enterprise environments
• Familiarity with observability, performance optimization, and cost management

Remote work available

• Mid‑Senior level

• Full‑time

• Information Technology and Design
• IT Services and IT Consulting, Software Development, and Business Consulting and Services

Referrals increase your chances of interviewing  by 2x