Job Summary :

We are looking for an experienced AI Application Engineer to build production-grade Generative AI applications. The ideal candidate should have hands-on experience developing LLM-powered solutions, designing high-quality RAG pipelines, implementing AI safety guardrails, and optimizing model performance for enterprise applications.

Key Responsibilities :

- Design, build, and deploy production-ready LLM applications.

- Develop multi-step LLM workflows using LangChain, LlamaIndex, or custom orchestration frameworks.

- Build and optimize RAG pipelines, including chunking, embeddings, vector search, reranking, and retrieval evaluation.

- Implement AI safety features such as prompt injection prevention, jailbreak detection, hallucination mitigation, and content safety.

- Work with NVIDIA AI technologies including NVIDIA NIM, NeMo, NeMo Guardrails, and NVIDIA Riva.

- Develop streaming AI APIs and optimize model quality, latency, scalability, and production monitoring.

- Build automated evaluation pipelines and feedback loops to continuously improve AI performance.

Required Skills :

- 4 to 7 years of software engineering experience with 2+ years in production LLM application development.

- Strong experience with Python, Async Programming, REST APIs, and AI service development.

- Expertise in Prompt Engineering, Chain-of-Thought, Few-shot Prompting, Multi-turn Conversations, Session Memory, and Streaming LLMs.

- Hands-on experience with LangChain, LlamaIndex, LLM orchestration, and conversational AI.

- Strong knowledge of RAG, Embeddings, Vector Databases, Hybrid Search, Reranking, RAGAS/TruLens, and Retrieval Optimization.

- Experience with NVIDIA NIM, NeMo Framework, NeMo Guardrails, NVIDIA Riva, and LLM deployment/inference.

- Expertise in AI Safety, Prompt Injection Prevention, Jailbreak Testing, Hallucination Detection, Content Safety, and Guardrails.

- Experience with LLM evaluation, A/B testing, latency profiling, model monitoring, and feedback loop design.

Nice to Have :

- Adaptive Learning or Personalization Engines

- Knowledge Graphs with RAG

- Multi-Agent AI Architectures

- ServiceNow API Integration

- Experience building AI applications on NVIDIA infrastructure

Preferred Experience :

- Built and shipped production LLM applications used by real customers.

- Designed AI safety and guardrails for customer-facing products.

- Built RAG evaluation pipelines for production release decisions.

- Optimized multi-step LLM pipelines for latency and scalability.

- Hands-on experience with NVIDIA NIM or NeMo in production environments is highly preferred.