AI Engineer

Primis; New York (NY); On-site; USD 100,000 - 150,000; Full time

Job summary

Primis is seeking an engineer in New York to build AI infrastructure and scalable frameworks for intelligent automation. You will create reusable SDKs and APIs, integrate LLM orchestration, and ensure observability in production systems.

The role requires solid Python skills and experience with agent systems, as well as collaboration with cross-functional teams. Additional responsibilities include embedding safety features and documenting engineering standards.

Qualifications

• Solid Python engineering skills with hands-on experience in AI systems.
• Experience with agent orchestration frameworks and multi-agent design.
• Proven ability to integrate LLMs into products.
• Platform engineering mindset to build usable SDKs and APIs.
• Experience with observability in AI systems.

Responsibilities

• Build AI infrastructure and scalable agent frameworks for intelligent automation.
• Create SDKs and APIs for engineering and business teams.
• Integrate LLM orchestration and routing into AI systems.
• Ensure full observability for agent workflows in production.
• Embed moderation and safety features from the start.
• Document system architecture and SDK usage.
• Collaborate with cross-functional teams to define best practices.

Skills

Python engineering skills

Agent orchestration frameworks

LLM integration

SDK and API development

Observability and tracing

AI safety concepts

Communication skills

Fintech exposure

Job description

Responsibilities

• You’ll be building the AI infrastructure that others build on, designing and shipping scalable agent frameworks and multi-agent systems that power intelligent automation across a regulated fintech environment
• Working alongside platform engineers, architects, and product teams, you’ll create the reusable SDKs and APIs that let engineering and business teams move fast without sacrificing reliability
• LLM integration will be a core part of your day to day, covering orchestration, routing, structured output, and standardising protocols like MCP and A2A across the platform
• You’ll take ownership of observability and tracing for agent workflows, making sure there’s full visibility into how AI systems are behaving in production
• Safety guardrails are not an afterthought here, you’ll be embedding moderation, PII filtering, and cost controls directly into the platform from the ground up
• You’ll contribute to architectural strategy and evaluate systems for production readiness, bringing a strong opinion on scalability and operational tradeoffs
• Documentation is part of the craft in this role, you’ll produce clear, well-structured guidance on system architecture, SDK usage, and engineering standards
• Collaboration is key, you’ll partner closely with cross-functional teams to define best practices and raise the bar on how AI is built and deployed across the organisation

Skills Needed

• Solid Python engineering skills with hands-on experience building production AI and agentic systems, TypeScript or Java exposure is a bonus
• Practical experience with agent orchestration frameworks, particularly AWS Strands SDK, and a strong grasp of multi-agent system design including async Python patterns
• Proven ability to integrate LLMs into real products, including prompt engineering, structured output design, and context management
• A platform engineering mindset, you know how to build developer-friendly SDKs and APIs that others actually enjoy using
• Experience implementing observability and tracing for AI systems, with tooling such as OpenTelemetry or Langfuse being a plus
• Familiarity with AI safety concepts including guardrails, moderation, and cost controls in a production setting
• Strong written and verbal communication skills, with an ownership mentality and a focus on code quality and maintainability
• Exposure to fintech or other regulated industries is advantageous but not essential