Job Description: Applied AI Engineer (RAG + Local Models)
Experience: 24 Years
Location: Work From Office
Employment Type: Full-time
About Opkey
Opkey is the leading Cloud Application Lifecycle Management (CALM) platform for Oracle, Workday, Salesforce, Coupa, and more. It cuts the costs and risks that drag down implementations and ongoing change, helping you go live on time, get more from your cloud app investments, and reach AI readiness faster. Opkey's 20+ AI agents manage all five
phases of the cloud application lifecycleDefine, Design, Configure, Test, and Train.
Whether it's a new implementation, a platform update, or a businessasusual change, Opkey handles it all: updates validated in hours, selfhealing tests, endtoend integrations assured, configurations synced, and training updated in real timeall delivered in a single unified platform instead of a patchwork of disconnected tools.
Powered by Argus, a domainspecific AI model trained on decades of expertise and terabytes of enterprise application data, Opkey automates configuration, testing, change impact analysis, and training across these applicationscutting manual effort by 80%, enabling 30% faster golives, and slashing downtime risk by 92%
Role Overview
We are looking for a Applied AI Engineer who can build real-world AI applications using local large language models (LLMs). The role focuses on Retrieval-Augmented Generation (RAG), prompt engineering, and local inference frameworks to create secure enterprise AI systems. You will integrate LLM capabilities with backend services, APIs, and lightweight user interfaces to build end-to-end AI applications.
Key Responsibilities
- Build and deploy AI applications using local LLM models.
- Design and implement Retrieval-Augmented Generation (RAG) pipelines.
- Develop and optimize prompts for reliable LLM responses.
- Work with local inference tools such as LM Studio and Ollama.
- Develop backend services and AI pipelines using Python.
- Design and expose REST APIs for AI services.
- Document APIs using Swagger / OpenAPI.
- Implement vector search and document retrieval pipelines.
- Build simple user interfaces or dashboards using AI-assisted (vibe coding) approaches for rapid prototyping.
- Optimize LLM performance for latency, accuracy, and cost efficiency.
- Collaborate with product and engineering teams to deploy AI features into production.
Required Skills
- 24 years of experience in Python development.
- Hands-on experience building LLM or Generative AI applications.
- Strong understanding of RAG architecture and vector search.
- Experience working with local LLM frameworks such as LM Studio or Ollama.
- Experience building REST APIs.
- Familiarity with Swagger / OpenAPI API documentation.
- Strong prompt engineering and prompt optimization skills.
- Experience working with embeddings and document ingestion pipelines.
- Familiarity with frameworks such as LangChain or LlamaIndex.
Good to Have
- Experience with open-source LLMs such as Llama or Mistral.
- Experience with vector databases (Qdrant, Chroma).
- Basic frontend/UI development skills.
- Experience deploying AI systems on cloud or on-prem infrastructure.
- Understanding of GPU inference, quantization, or model optimization.
Candidate Evaluation (Practical Skill Expectations)
- Ability to build a simple RAG pipeline using a local LLM and document dataset.
- Ability to expose the AI functionality via a REST API.
- Ability to create a small UI or demo application using AI-assisted coding tools.
- Understanding of prompt tuning and evaluation of LLM responses.
Example Projects the Candidate May Work On
- Enterprise knowledge assistants
- Document search and Q&A systems
- Internal developer copilots
- AI-powered data extraction and summarization systems
Skills: genai,llm,graphdb,python,openai,ollama,rag
