Job Title: AI Implementation Engineer (On-Site)
Location: Office-based (Full-Time, In-Office)
Experience: 3–6 Years
About The Role
We are seeking an on-site AI Implementation Engineer to anchor our corporate innovation lab. Working closely with our product and security teams in a physical office setting, you will deploy enterprise-grade Large Language Models (LLMs), build retrieval-augmented generation (RAG) loops, and optimize vector search indexes (e.g., Qdrant/Typesense) on-premise and in secure cloud-hybrids.
Key Responsibilities
- Work full-time from our development center, collaborating daily with product managers, security officers, and backend squads.
- Architect, fine-tune, and integrate AI models (OpenAI API, Anthropic, or open-source weights like Llama/Mistral) into internal core applications.
- Set up and maintain high-performance vector database implementations and data ingestion pipelines.
- Ensure strict data privacy compliance, handling tokenization and proprietary data filters under strict internal security frameworks.
- Troubleshoot live deployment bottlenecks, model drift, and latency issues via active whiteboard sessions and rapid in-person prototyping.
Required Skills & Qualifications
- Work Mode: 100% On-site commitment with daily physical attendance.
- Tech Stack: Advanced Python (FastAPI), LangChain/LlamaIndex, vector databases (Qdrant, Pinecone), and Docker containerization.
- Collaboration: Excellent verbal communication and teamwork skills for fast-paced, whiteboarding-heavy office environments.
Skills: cloud,api,fastapi,langchain,python,langraph,vector