Hands-on AI Technical Lead

Hands-on AI Technical Lead – Production LLM Systems

AllysAI · Full-time · Remote

About AllysAI

AllysAI rebuilds enterprise operations as AI-native systems. We develop and deploy production AI on our AllysOS platform for organisations in banking, pharmaceuticals, government and energy.

We’re headquartered in Abu Dhabi, with offices in New York and Lausanne.

The role

You’ll take technical ownership of enterprise AI systems—from architecture and implementation through evaluation, deployment and ongoing reliability—and lead the engineers building them with you.

This is a hands-on role: most of your time will go into designing, coding, testing and shipping. You’ll also work directly with client technical teams, explain your decisions and take responsibility for delivery.

We’re looking for someone who can choose the right approach for a problem, understand where it can fail, and build a system that remains dependable with real users and sensitive data.

What you’ll do

• Design the architecture: decide when to use deterministic workflows, RAG, a single agent or multiple agents. Explain the trade-offs behind your choices of models, frameworks and infrastructure.
• Build the system: implement Python services, APIs, retrieval pipelines, tool integrations and agent workflows, including MCP where appropriate.
• Build document AI: develop OCR, extraction, classification and cross-document validation pipelines, with clear handling of missing, conflicting or uncertain information.
• Own evaluation and robustness: create representative test datasets, measure retrieval and output quality separately, investigate failures, and establish regression tests and release criteria.
• Deploy and operate: select deployment approaches for client-controlled cloud or on-premises environments, and manage monitoring, latency, cost, reliability and recovery.
• Build security into the design: enforce access controls and data boundaries, protect sensitive information, and control what agents can access and do.
• Lead delivery: divide work across engineers, review code, set standards and work with client teams through integration, testing and production handover.

What you bring

• 5+ years of professional software engineering experience, including at least 2 years building and operating production LLM or generative AI systems used by real users.
• Strong Python and backend engineering skills, including APIs, databases, integrations and automated testing.
• Hands-on experience with RAG, vector search, re-ranking, structured outputs and agent/tool orchestration.
• Practical experience evaluating AI systems beyond successful demos: test-set design, error analysis, measurable quality and production safeguards.
• Experience taking systems into production using Docker, CI/CD, monitoring and secure deployment practices.
• Evidence of leading engineers while remaining directly involved in implementation.
• Clear English and the ability to discuss architecture, delivery risks and technical trade-offs with clients.
• A disciplined approach to AI-assisted development: able to explain which coding tools you use, how they help, and how you verify the resulting code.

Particularly relevant experience

• Azure, including Azure OpenAI, AI Search, Document Intelligence and API Management. Strong AWS or GCP experience is also relevant.
• Banking, pharmaceuticals, healthcare, government or other regulated environments.
• Private networking, locally hosted models, restricted-connectivity environments or on-premises deployments.
• Production document workflows involving complex layouts, multilingual content or human review.

What we offer

• Competitive compensation based on experience and role scope.
• Flexible time off.
• Hands-on technical ownership and direct exposure to enterprise clients.
• The opportunity to build reusable capabilities across multiple production deployments.