Key Responsibilities
Application Design &
Architecture: Lead the high-level design of distributed microservices. You will decide when to leverage the performance of Java/Spring Boot, the flexibility of Python, or the enterprise integration of .NET Core.
Generative AI Integration: Architect and maintain Retrieval-Augmented Generation (RAG) systems. Integrate LLMs (OpenAI, Gemini, or Llama) into production workflows to enhance user experience and automate internal operations.
Cloud-Native Deployment: Own the end-to-end lifecycle of services. Use Docker and Kubernetes (EKS/GKE/AKS) to ensure high availability and auto-scaling.
Automated Pipelines: Design and optimize CI/CD pipelines (GitHub Actions, GitLab CI, or Jenkins) to ensure "security-first" deployments and rapid iteration.
Mentorship &
Governance: Review code for both human-written and AI-assisted contributions. Set the standard for clean code, system observability, and ethical AI usage.
Technical Requirements
Languages: Mastery of at least two: Java (Spring Boot),
Python (FastAPI/Django), or .NET 8+.
Generative AI: Hands-on experience with LangChain or LlamaIndex. Familiarity with Vector Databases (Pinecone, Milvus, or Weaviate) and prompt engineering.
Infrastructure: Proven experience with Kubernetes orchestration and Terraform/Pulumi for Infrastructure as Code (IaC).
DevOps: Expert knowledge of CI/CD patterns, including blue-green deployments and automated rollbacks.
Data &
Analysis: Robust ability to analyze system bottlenecks and design data schemas (SQL &
NoSQL) that support high-concurrency AI applications.
Preferred Qualifications
Experience fine-tuning small language models (SLMs) for specific domain tasks.
Understanding of LLMOps (monitoring hallucinations, token cost optimization, and latency tracking).
Experience in highly regulated industries (Fintech, Healthcare) where security-first design is paramount.