AI Engineer (Senior/Mid Level)

Company Description

Infinite Control is a technology-focused company specializing in advanced automation and intelligent systems. The organization is committed to leveraging artificial intelligence to solve complex real-world problems and improve operational efficiency for its clients. Team members collaborate across disciplines to design, build, and deploy AI-driven solutions that deliver measurable impact

Job Description

We are looking for an AI Engineer to transform complex business problems into reliable, secure, and production-ready AI solutions. You will design and develop enterprise AI applications, including RAG systems, AI agents, document intelligence pipelines, and AI-powered business automation, integrated with ERP, CRM, APIs, and other enterprise systems.

Key Responsibilities

• Design and build enterprise-grade LLM applications, RAG systems, AI agents, and document understanding solutions.

• Develop agentic workflows that use tools and APIs, manage state and memory, and support human-in-the-loop escalation.

• Integrate AI solutions with ERP, CRM, databases, and enterprise APIs.

• Transform AI prototypes and proof-of-concepts into scalable, reliable, secure, and production-ready applications.

• Establish evaluation and testing processes to measure retrieval quality, tool-call accuracy, task completion, hallucinations, and regressions.

• Implement safeguards against AI security risks such as prompt injection, excessive agency, tool abuse, and data leakage

Requirements

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

• Strong experience with LLM application development, including prompt/context engineering, structured outputs, and function/tool calling.

• Hands-on experience with Advanced RAG, including chunking, metadata filtering, vector search, and retrieval optimization.

• Experience designing AI agents and agentic workflows, including planning, tool use, state, and memory.

• Ability to determine when to use deterministic workflows vs. autonomous agents based on business and reliability requirements.

• Strong understanding of AI evaluation and security, including the principle that LLMs are untrusted components and must never act as the authorization layer.

• Strong Python development skills with experience in Git and API integration.

• Experience with FastAPI or similar backend frameworks.

• Strong knowledge of PostgreSQL.

• Experience with async programming and background processing.

• Understanding of production software engineering, reliability, testing, scalability, and maintainability.

Nice to Have

• Frameworks: LangGraph, LlamaIndex, Hugging Face, vLLM, Ollama.

• Data & Knowledge: pgvector, vector databases, Knowledge Graphs.

• Advanced ML: LoRA/QLoRA fine-tuning, quantization, PyTorch.

• Experience deploying and operating LLM/AI systems in production.