AI Lead Developer

About

We’re looking for a hands-on AI Lead Developer to own the technical direction of our AI platform. If you’re ready to lead a team building production LLM systems for a high-profile enterprise product in the aviation industry, you’ve come to the right place!

You will lead the AI engineering team, define the architecture of our AI platform, and drive the delivery of intelligent features end-to-end — from LLM pipelines and knowledge graphs to mobile AI experiences and evaluation infrastructure. You will work directly with the CTO and product leadership to shape the AI roadmap, ensure engineering quality, and grow the team. This role combines technical depth with team leadership and cross-functional collaboration.

Windmill is a boutique digital product delivery company. Our team of designers, strategists and engineers love to create great experiences. We design and develop delightful and functional digital products that solve tough problems and enable new opportunities for enterprises in complex industries, such as banking & finance, healthcare and compliance.

For more information, please check the company website at https://www.windmillsmartsolutions.com/

Responsibilities

• Lead and grow the AI engineering team: hire, mentor, conduct code reviews, and create development opportunities for engineers
• Own the end-to-end architecture of the AI platform — RAG pipelines, multi-LLM orchestration, document ingestion, semantic search, and assistant workflows
• Define technical standards and patterns across AI services (Python, FastAPI, LangChain / LangGraph) and ensure their consistent adoption
• Partner with the backend team (NestJS / Prisma / PostgreSQL / Redis) and mobile team (Flutter / BLoC / Firebase) to align on API contracts and integration points
• Drive the design and evolution of the knowledge graph layer (Neo4j) and vector search infrastructure (OpenSearch)
• Lead the evaluation strategy: define benchmarks for RAG systems, track LLM/RAG quality metrics (faithfulness, relevance, hallucination rate, RAGAS-style metrics), and own the MLflow experiment lifecycle
• Make architectural decisions on multi-provider LLM routing (OpenAI, Anthropic Claude, Google Gemini) including cost, latency, and quality trade-offs
• Ensure production reliability through observability (OpenTelemetry, Prometheus, Sentry) and structured incident response
• Collaborate with product management to translate business requirements into AI-first technical roadmaps
• Champion responsible AI practices: prompt injection defense, data privacy, output safety, and audit trails
• Work in an AWS cloud environment (S3, KMS, Secrets Manager, IAM) and manage infrastructure concerns with the DevOps team

Requirements

• 7+ years of professional software engineering experience, with 3+ years leading AI/ML engineering teams or projects
• Proven track record of hiring, leading, and mentoring engineers in a tech lead or staff engineer capacity
• Deep Python expertise including async/concurrent systems and production-grade API services
• Architecture-level understanding of LLM orchestration (LangChain, LangGraph, or equivalent) and RAG system design
• Hands-on production experience with multiple LLM providers: OpenAI, Anthropic Claude, Google Gemini
• Strong understanding of vector search and embedding strategies; experience with OpenSearch or equivalent
• Experience with FastAPI, Pydantic, SQLAlchemy/Alembic, and PostgreSQL at scale
• Solid knowledge of Redis for caching and job queues; familiarity with BullMQ or equivalent
• AWS cloud experience: S3, IAM, KMS, Secrets Manager; Docker and CI/CD pipelines
• Experience defining and running LLM evaluation pipelines; familiarity with MLflow or comparable experiment tracking
• Ability to communicate complex technical decisions clearly to both engineering teams and non-technical stakeholders
• Upper-intermediate English (B2+)

Will Be a Plus

• Experience with Neo4j or knowledge graph design for AI applications
• Familiarity with NestJS / TypeScript and ability to contribute to backend API design
• Familiarity with the admin frontend stack (React, TypeScript, Vite, TanStack Query, Radix UI, Tailwind, MSAL) for steering AI-facing internal tooling
• Flutter / mobile AI integration experience (streaming LLM responses, voice assistants, on-device features)
• Knowledge of OCR and document processing pipelines (PyMuPDF, pdfplumber, Tesseract)
• Experience with OpenTelemetry-based observability and Prometheus alerting
• Background in aviation, technical documentation, or regulated industry AI compliance
• Contribution to open-source LLM tooling or published AI benchmarks

We Offer

• Competitive compensation
• Become a part of our international leadership team
• Real autonomy: define and evolve the technical direction of the AI platform
• Opportunities for leadership growth
• Friendly, collaborative environment with talented engineers
• Opportunity to make a meaningful impact on a product used by aviation professionals worldwide

If you’ve got the leadership skills, technical depth, and drive to shape a world-class AI platform, please send your CV immediately! =)