Experience: 2–3+ Years
Employment Type: Full-Time
Job Summary
We are hiring an AI / LLM Integration Engineer to develop enterprise-grade AI capabilities for an HR-EMS-GPT platform. The role involves building retrieval systems, integrating LLMs, optimizing AI responses, and ensuring secure access to organizational knowledge.
Key Responsibilities
- Build HR document Q&A systems
- Develop employee analytics assistants
- Design and manage prompt libraries
- Implement RAG pipelines
- Create secure retrieval workflows
- Reduce hallucinations and improve answer quality
- Add citations and source attribution
- Implement role-based AI access controls
- Monitor and optimize token usage
Required Skills
- OpenAI API
- Azure OpenAI
- LangChain or LlamaIndex
- Retrieval-Augmented Generation (RAG)
- Embeddings
- Vector Databases
- Prompt Engineering
- Document Parsing
- PDF, Excel, and Text Ingestion
- Guardrails and AI Safety
- Response Evaluation Frameworks
- Token Cost Optimization
Nice to Have
- Pinecone
- Qdrant
- Weaviate
- pgvector
- OpenSearch
- Enterprise AI implementations
- HRMS or ERP domain experience
Why Join Us?
- Build real-world AI products at enterprise scale
- Work on advanced LLM and RAG architectures
- Collaborate with experienced engineering teams
- Opportunity to influence product and AI strategy
Apply with your resume, GitHub profile, and AI project portfolio.
Benefits:
- Flexible schedule
- Paid sick time
Work Location: In person
