Lead AI Back-End Engineer

 The impact you’ll make as a Lead AI Back-End Engineer

 • Set the technical architecture for our agent powered platform, choosing the right mix of LLMs, retrieval technologies, agent frameworks, and microservice patterns to meet reliability, cost, quality, and latency targets. 

• Drive architecture for high throughput APIs built with .NET, C#, Python 3.11+, FastAPI async, SQLModel, and Semantic Kernel, from design documents through production rollout. 

• Lead multi agent orchestration across handoff, sequential, parallel, and supervisor patterns, combining knowledge grounded and tool calling agents across OpenAI GPT 5.6 Sol, Terra and Luna, Google Gemini 3.7 Flash, Anthropic Claude Sonnet 5 and Opus 5, xAI Grok 4.6, and future model providers. 

• Guide teams implementing Retrieval Augmented Generation on Azure AI Search, pgvector, Chroma, and equivalent vector and hybrid retrieval platforms, ensuring index quality, filtering, evaluation, and safety controls. 

• Own end to end CI/CD pipelines using Bitbucket Pipelines, Jenkins, or similar platforms, including linting, type checking, security scanning, testing, containerization, and deployment. 

• Mentor and hire engineers and adopt AI coding agents such as Cursor and Claude Code as engineering force multipliers while maintaining strong code quality, security, and review standards. 

• Champion observability and FinOps for LLM workloads using structured JSON logging, OpenTelemetry tracing, Langfuse, evaluation frameworks, and cost dashboards, keeping latency and cost per request within defined SLOs. 

• Partner with Product and Security to translate business goals, compliance requirements, emerging AI capabilities, and user feedback into a pragmatic technical roadmap. 

Must have experience 

• 7+ years building and scaling production backend systems, including 2+ years in a technical lead, staff, principal, or equivalent role. 

• Expert in REST API design and development using Python FastAPI or .NET C# APIs, with strong experience in dependency injection, middleware, profiling, performance optimization, and distributed systems. 

• Hands on leadership experience with Semantic Kernel or equivalent agent and LLM frameworks, including production agent orchestration, tool calling, structured outputs, and multi step workflows. 

• Delivered at least one production RAG system or pipeline using a vector or hybrid search platform such as Azure AI Search, pgvector, Chroma, or equivalent, with measurable latency and quality KPIs. 

• Deep PostgreSQL expertise plus SQLModel, SQLAlchemy 2, and Alembic migrations at scale. 

• Proven track record integrating multiple frontier and cost optimized model providers, such as OpenAI GPT 5.6, Gemini 3.x, Claude 5, Grok 4.x, or equivalent, including model routing, structured output, reasoning, tool calling, and fallback strategies. 

• Fluency with Poetry, Docker, GitHub Actions, Azure DevOps, Jenkins, or Argo, along with infrastructure as code fundamentals and blue green or canary release strategies. 

• Strong people leadership through code reviews, architectural guidance, technical mentoring, roadmap planning, hiring, and cross team communication. 

Nice to have 

• Experience with message queue and event driven architectures using RabbitMQ, Kafka, Azure Service Bus, or equivalent. 

• Experience with GPU inference fleets, self hosted open weight models, or serverless model hosting. 

• Experience with model gateways, intelligent model routing, MCP, agent interoperability, prompt caching, and LLM cost optimization. 

• Familiarity with automatic evaluation pipelines, agent evaluations, LLM as judge techniques, safety guardrails, and cost aware prompt and context engineering. 

Why join the Newfold AI team? 

You’ll steer the core intelligence behind our AI products, building an LLM agnostic, agent driven platform that serves millions of users while meeting enterprise grade standards for reliability, security, governance, and economics. If you thrive on significant technical challenges, enjoy mentoring strong engineers, and want the opportunity to shape both architecture and engineering culture, we’d love to meet you.