Senior AI Engineer

Senior AI Engineer

Location: Remote (US) | Type: Full Time | Experience: 10+ years | Pay: $162K-$205K

About the Role

We're hiring a Senior AI Engineer to build the platform layer that decides how AI requests get handled. Not every problem needs a large model, and the systems you build will weigh the options (simple rules, search, smaller models, LLM calls, or a person) and pick the one that gets the right answer at the right cost.

Our client is a growth-stage consumer fintech with a large customer base and a growing set of AI-powered experiences, both customer-facing and internal. You'll join their AI platform group, so what you build becomes shared infrastructure for engineering teams across the company.

This role suits someone who has run AI systems in production for real users and knows the hard part starts after the demo.

What You'll Do

• Design routing logic that matches each request to the best way to handle it
• Build flows that work out what a user is asking, follow up when the request is unclear, and escalate when confidence is low
• Run head-to-head evaluations across approaches and models, then turn the results into clear recommendations
• Harden orchestration for production with fallbacks, retries, timeouts, and well-defined output schemas
• Connect agents to internal services and third-party tools safely, with proper auth and guardrails around every action
• Partner with security and compliance on threats like prompt injection and on protecting sensitive data
• Turn one-off solutions into reusable building blocks other teams can pick up
• Track how AI features behave in production and use that data to improve them
• Use AI coding tools every day, and know when not to trust them

Qualifications

• 10+ years building software professionally, including AI or ML work that shipped to real users
• A bachelor's degree or higher in a relevant field, or equivalent hands-on experience
• Strong Python or TypeScript, with solid API design, testing, and distributed systems fundamentals
• Real experience with LLM function calling, schema-constrained outputs, retrieval-augmented generation, and multi-step agent workflows
• Comfort measuring AI systems on accuracy, speed, uptime, and cost
• Production experience across cloud deployments, CI/CD, monitoring, access control, secrets handling, and incident recovery
• Good judgment about when a model is the right tool and when a simpler approach wins
• Works well independently inside shared engineering standards and collaborates easily with product, security, and compliance partners

Nice to Have

• Experience with a major cloud provider's managed AI services (GCP, Azure, or AWS)
• Semantic routing, self-hosted or open-weight models, or MCP
• Building internal agent frameworks or developer platforms
• Background in financial services or another regulated, high-accuracy domain

Why Join Us

You'll work on a platform team whose output reaches customers directly and powers tools other engineers depend on. Accuracy matters in this domain, so the team values engineers who can explain how and why a system reached its answer.

If you want to build AI that people can rely on, not another prototype, this role is worth a conversation.

To apply, click Apply on LinkedIn and visit eliosai.com/browse-jobs