Senior AI Platform Engineer for Enterprise AI Systems

Talantir; New York (NY); On-site; USD 180,000 - 240,000; Full time

Job summary

Talantir is seeking an AI Full-Stack / Systems Engineer to design scalable backend services and platform components powering enterprise AI apps and agent-based workflows. You will focus on LLM integrations, AI orchestration, and production-grade AI infrastructure used by multiple teams.

You will collaborate with platform, architecture, and application teams to build secure, governed systems at scale, with emphasis on reliability, cost visibility, and safety controls.

Qualifications

• Backend and platform engineering experience required.
• Experience with distributed systems and microservices.
• Hands-on with LLMs, RAG architectures, or AI agent frameworks.
• Experience integrating AI APIs (OpenAI, Anthropic, Bedrock, etc.).
• Experience with AWS or other cloud platforms.
• Familiarity with vector databases and embeddings for retrieval.
• Proficient with RESTful APIs and containerization (Docker).

Responsibilities

• Build backend services supporting AI agents and multi-step AI workflows
• Develop LLM integration layers and model service APIs
• Implement RAG pipelines including document ingestion, embeddings, and vector retrieval
• Build orchestration frameworks connecting models, tools, and enterprise APIs
• Implement AI safety controls, guardrails, and policy enforcement
• Develop observability, monitoring, and cost tracking for AI systems
• Integrate AI systems with enterprise platforms and internal services

Skills

Backend engineering

Distributed systems

LLMs / RAG / AI agents

AI integrations

AWS / cloud platforms

Vector databases / embeddings

REST APIs / Docker

Tools

Docker

Job description

Talantir is seeking an AI Full-Stack / Systems Engineer to design scalable backend services and platform components powering enterprise AI apps and agent-based workflows. You will focus on LLM integrations, AI orchestration, and production-grade AI infrastructure used by multiple teams.

You will collaborate with platform, architecture, and application teams to build secure, governed systems at scale, with emphasis on reliability, cost visibility, and safety controls.