Senior AI Application Engineer

• Design and build enterprise LLM applications
• Develop scalable RAG pipelines and evaluation frameworks
• Optimize prompt engineering, retrieval quality, and model accuracy
• Implement AI safety, guardrails, hallucination detection, and security controls
• Build multi-step LLM orchestration workflows
• Improve latency, scalability, and production reliability
• Collaborate with product, platform, and engineering teams to deliver AI-powered solutions

Why Join?

• Build next-generation enterprise AI products
• Work on LLMs, RAG, Multi-Agent AI, and Generative AI technologies
• Solve challenging AI quality, safety, and scalability problems
• Collaborate with experienced AI engineers and product leaders
• Opportunity to shape production AI systems used by real customers

Pay: $150,000.00 - $170,000.00 per year

We are seeking a Senior AI Application Engineer with deep expertise in LLMs, RAG, Prompt Engineering, AI Safety, and Production AI Systems. You will build and own enterprise-grade AI applications that power intelligent learning experiences, conversational AI, adaptive recommendation engines, and multi-modal AI solutions. This is a production engineering role focused on building reliable, scalable, and secure AI products-not research or proof-of-concepts., * 10+ years of overall software engineering experience

• 2+ years building production-grade LLM applications
• Strong expertise in Python
• Hands-on experience with RAG (Retrieval-Augmented Generation)
• Prompt Engineering and LLM optimization
• LangChain, LlamaIndex, or custom orchestration frameworks
• AI Safety, Guardrails, Prompt Injection & Jailbreak Prevention
• RAG Evaluation Frameworks (RAGAS, TruLens, or equivalent)
• Vector Databases, Embeddings, and Semantic Search
• Production AI monitoring, evaluation, and optimization
• API development and AI service deployment

Preferred Skills

• NVIDIA AI ecosystem
• NeMo Guardrails
• Knowledge Graphs
• Multi-Agent AI Systems
• Adaptive Learning Platforms
• ServiceNow API Integration
• Hybrid Search (BM25 + Vector Search), * production LLM applications: 1 year (Preferred)