AI Engineer(NVIDIA NIM, NeMo, NeMoGuardrails)

Dice is the leading career destination for tech experts at every stage of their careers. Our client, Kasmo Inc., is seeking the following. Apply via Dice today!

Day-to-Day Responsibilities

Design, develop, and optimize production-grade LLM-powered applications

Own AI quality, RAG accuracy, prompt engineering, and AI safety across multiple applications

Develop and maintain multi-step LLM orchestration pipelines using LangChain, LlamaIndex, or custom frameworks

Implement and optimize RAG pipelines including chunking strategies, embedding selection, reranking, and hybrid search

Design multi-turn conversational AI experiences with context management and session memory

Integrate NVIDIA technologies including NIM, NeMo, NeMoGuardrails, and Riva into enterprise AI applications

Build automated evaluation pipelines for model quality, hallucination detection, regression testing, and release gating

Perform latency profiling and optimization across multi-step LLM call chains

Implement AI safety guardrails including prompt injection prevention, jailbreak mitigation, and topical control

Collaborate with globally distributed engineering and product teams to deliver scalable AI solutions

Support deployment, monitoring, and continuous improvement of AI applications in production environments

Basic Qualifications:

4–7 years of software engineering experience with at least 2 years focused on production LLM application development

Expert-level experience with Python for AI/ML application development and async programming

Strong expertise in prompt engineering including system prompts, few-shot prompting, and instruction tuning

3+ Years of Hands-on experience with multi-step LLM orchestration frameworks such as LangChain or LlamaIndex

3+ Years of Experience designing and optimizing RAG pipelines and retrieval systems

3+ Years of Experience with vector databases, similarity search tuning, and reranking techniques

3+ Years of Hands-on experience with NVIDIA NIM, NeMo, NeMoGuardrails, and Riva

3+ Years of Experience implementing AI safety and guardrails for customer-facing applications

Strong knowledge of automated AI evaluation frameworks such as RAGAS or TruLens

3+ Years of Experience profiling and optimizing latency in multi-step AI pipelines

Ability to work onsite in Santa Clara, CA

Preferred Qualifications

Experience with adaptive learning systems or recommendation engines

Knowledge graph integration experience with RAG architectures

Experience with multi-agent orchestration patterns

ServiceNow API integration experience

Prior experience building AI products on NVIDIA infrastructure

Experience with streaming LLM response handling and real-time AI applications

Technology Stack

Python

LangChain

LlamaIndex

NVIDIA NIM

NeMo

NeMoGuardrails

NVIDIA Riva

Vector Databases

RAGAS / TruLens

LLM APIs and orchestration frameworks

Education

Bachelor’s degree in Computer Science, Engineering, Artificial Intelligence, or equivalent work experience.