AI Engineer

LinkGroup is the employer for this role.

• Senior level experience with shipping LLM-driven applications into live production environments.
• Advanced Python proficiency with strong experience in software design, API contracts, and scalable backend services.
• Practical experience with major AI platforms and foundation models such as OpenAI, Azure OpenAI, or AWS Bedrock.
• Solid grasp of prompt design, structured data outputs, context window optimization, and external tool execution.
• Hands-on experience establishing evaluation frameworks, guardrails, fallback routines, and operational testing.
• Pragmatic engineering approach focused on code maintainability, continuous delivery, and technical curiosity.

Bonus Qualifications:

• Exposure to LLM orchestration frameworks (RAG, LangChain, MCP, Graph databases).
• Experience with infrastructure as code (IaC).
• Experience with rapid prototyping tools like Streamlit, Jupyter.
• Knowledge of Java/Kotlin or classical NLP tasks (e.g., PII detection, classification).

• Architect, build, and operate resilient Python-based backend microservices and APIs powered by LLMs.
• Design end-to-end LLM integration workflows, including structured outputs, function/tool calling, prompt optimization, and context management.
• Implement AI safety controls, output validation layers, operational fallbacks, and robust error handling.
• Establish comprehensive observability across production AI applications using modern metrics, logging, tracing, and evaluation tools.
• Translate ambiguous functional requirements into clean, production-ready technical solutions in partnership with product and engineering teams.
• Continuously refine system performance through model iteration, prompt tuning, cost optimization, and contract definitions.