Senior AI Engineer; LLM & Agent Systems — Platform

Full time | Calliere | United States

Posted On 04/06/2026

$200,000 - $400,000 USD based on seniority

Work Experience LLM, agent systems, AI platform, model evaluation, orchestration, distributed systems, reliability engineering, AI infrastructure, vector search, retrieval systems, observability, API development, guardrails, cost optimization

Technology

City New York

State/Province New York

10007

Role Summary

This role focuses on designing and scaling reusable AI-driven workflows, particularly those powered by large language models and autonomous agents. You will build foundational components and abstractions that enable multiple internal teams to rapidly develop and deploy intelligent systems. The position emphasizes system reliability, evaluation rigor, and thoughtful tradeoffs in model and tooling selection.

Core Ownership Areas

Develop reusable agent-based workflows to accelerate delivery across multiple projects.

Define and maintain evaluation standards to ensure consistent model performance over time.

Improve system reliability across key dimensions such as accuracy, latency, and robustness.

Build shared APIs and platform components used broadly across engineering teams.

Key Responsibilities

Design and implement orchestration patterns for LLM-powered agents.

Evaluate and select models, tools, and providers based on performance, cost, and reliability.

Build testing frameworks, evaluation pipelines, and monitoring systems for AI outputs.

Implement safeguards, fallback mechanisms, and cost optimization strategies.

Collaborate with platform and backend engineers to integrate AI capabilities into scalable services.

Identify repeatable patterns across projects and convert them into reusable platform features.

Required Experience

Strong background in building production-grade distributed systems or platform infrastructure.

Practical experience developing and deploying LLM-based or agent-driven systems.

Demonstrated ability to design for reliability, observability, and cost efficiency.

High standards for code quality and system design.

Nice-to-Have Experience

Familiarity with retrieval systems, embeddings, or context management pipelines.

Experience working within regulated or security-conscious environments.

Approach to Work

Prioritizes measurable quality through structured evaluation and testing.

Designs systems for reuse, scalability, and clean abstraction layers.

Focuses on building solutions that generalize beyond a single use case or team.