Staff+ AI Platform Engineer (Remote)

Aleph; Philippines; Remote; PHP 11,152,000 - 16,109,000; Full time

Job summary

Aleph in the Americas is hiring a Staff+ Engineer to own the AI foundation and the eval infrastructure. You will lead model routing, the proxy layer, context management, and tool design, shipping features end to end from v0 through the optimization loop.

You’ll define evals with customers and finance-domain experts, build observability into agent behavior, and drive pragmatic, high-quality software. Remote-first role with a focus on the Americas.

Qualifications

• Experience shipping production LLM systems including evals and context management.
• Proven ability to ship v0s and iterate to production with eval-driven quality.
• Strong judgement on design and pragmatic incremental shipping.
• Experience with LLM APIs and agent frameworks; shipped user-facing products.
• Goal to deploy production systems, not pure research.

Responsibilities

• Own the AI foundation product teams build on: model selection and routing, the model proxy layer, context management, and tool design
• Own eval infrastructure. Work with customers and finance domain experts to define what excellent output looks like, then encode it in evals every team can run - in FP&A, a wrong answer ends up in someone's board deck
• Ship agentic features end to end, from v0 through the optimization loop: prompt and context engineering, caching, parallel tool calls, subagent patterns
• Build observability into agent behavior so we can profile it, find bottlenecks, and decide what to fix with data
• Track what's changing in agentic systems and bring the practices that prove out into how we build

Skills

LLM systems

Eval infrastructure

Model routing

Agent frameworks

Context management

Observability

Performance optimization

Tools

OpenAI API

LangChain

Prometheus

Job description

Aleph in the Americas is hiring a Staff+ Engineer to own the AI foundation and the eval infrastructure. You will lead model routing, the proxy layer, context management, and tool design, shipping features end to end from v0 through the optimization loop.

You’ll define evals with customers and finance-domain experts, build observability into agent behavior, and drive pragmatic, high-quality software. Remote-first role with a focus on the Americas.