Solution Lead/ JAVA TECH LEAD

Connexions; Carolina Beach (NC); On-site; USD 150,000 - 210,000; Full time

Job summary

Connexions in the United States is seeking an accomplished backend/AI engineer to design and productionize cloud-native services and LLM inference pipelines. You will develop Python APIs and microservices with FastAPI and implement agentic AI workflows using LangChain/LangGraph.

Role requires deep experience in LLM capabilities, embeddings, vector search, model versioning, and robust data engineering. Familiarity with Kubernetes, Helm, and Azure AKS is preferred; strong observability and CI/CD

Qualifications

• 13+ years of experience in IT and building cloud-native backend services.
• Experience productionizing AI/LLM inference pipelines.
• Design and develop Python-based APIs and microservices (FastAPI, async patterns).
• Implement and optimize LLM capabilities including embeddings, RAG, vector search, prompts.
• Package, serve, and monitor models for real-time and batch inference.
• Build event-driven, resilient integrations and containerized services with Kubernetes and Helm deployments.
• Establish observability, SLOs, CI/CD automation, testing.
• Apply systems design principles (concurrency, caching, reliability, rate limiting) and robust data engineering.

Responsibilities

• Build and productionize cloud-native backend services and AI/LLM inference pipelines.
• Design and develop Python-based APIs and microservices (FastAPI, async patterns) and agentic AI workflows using LangChain/LangGraph.
• Implement and optimize LLM capabilities including embeddings, RAG, vector search, prompt/context engineering, and model versioning.
• Package, serve, and monitor models for real-time and batch inference, ensuring operational readiness and performance.
• Build event-driven, resilient integrations and containerized services, with hands-on Kubernetes debugging and Helm-based deployments.
• Establish observability, SLOs, CI/CD automation, testing.
• Apply strong systems design principles (concurrency, caching, reliability, rate limiting) and robust data engineering practices.
• Cloud exposure preferred (Azure/AKS, managed services), with bonus experience in performance tuning, frontend collaboration, and model governance/monitoring.

Skills

Python programming

Cloud architecture

LLM / AI concepts

API design

Distributed systems

Kubernetes debugging

Tools

FastAPI

LangChain

LangGraph

Kubernetes

Helm

Azure AKS

CI/CD tooling

Job description

Job Description

Must Have Technical/Functional Skills

• 13+ years of experience with IT
• Build and productionize cloud native backend services and AI/LLM inference pipelines.
• Design and develop Python-based APIs and microservices (FastAPI, async patterns) and agentic AI workflows using LangChain/LangGraph.
• Implement and optimize LLM capabilities including embeddings, RAG, vector search, prompt/context engineering, and model versioning.
• Package, serve, and monitor models for real-time and batch inference, ensuring operational readiness and performance.
• Build event driven, resilient integrations and containerized services, with hands‑on Kubernetes debugging and Helm‑based deployments.
• Establish observability, SLOs, CI/CD automation, testing
• Apply strong systems design principles (concurrency, caching, reliability, rate limiting) and robust data engineering practices.
• Cloud exposure preferred (Azure/AKS, managed services), with bonus experience in performance tuning, frontend collaboration, and model governance/monitoring.

Roles & Responsibilities

• Build and productionize cloud native backend services and AI/LLM inference pipelines.
• Design and develop Python-based APIs and microservices (FastAPI, async patterns) and agentic AI workflows using LangChain/LangGraph.
• Implement and optimize LLM capabilities including embeddings, RAG, vector search, prompt/context engineering, and model versioning.
• Package, serve, and monitor models for real-time and batch inference, ensuring operational readiness and performance.
• Build event driven, resilient integrations and containerized services, with hands‑on Kubernetes debugging and Helm‑based deployments.
• Establish observability, SLOs, CI/CD automation, testing
• Apply strong systems design principles (concurrency, caching, reliability, rate limiting) and robust data engineering practices.
• Cloud exposure preferred (Azure/AKS, managed services), with bonus experience in performance tuning, frontend collaboration, and model governance/monitoring.