Software Engineer II – AI Engineer (w/ skills in Deployment)

Robert Half • San Ramon, CA

3d

About The Position

Robert Half is seeking a Software Engineer II – AI Engineer who will analyze, design, program, debug, test, implement, deploy, and support software enhancements and new applications using Generative AI technologies. This role contributes to the development and production deployment of GenAI-enabled applications, including LLM-powered workflows, RAG pipelines, and AI-driven user experiences. This role supports SDLC documentation across all phases, with a focus on deployment, evaluation, observability, safety, and monitoring. It also interacts with users to define requirements and support applications in production.

Requirements

• 4+ years of experience in IT or a related field.
• 2+ years of software engineering experience.
• 1+ year of experience in GenAI deployment.
• Experience with AI coding agent–augmented development.
• Experience with cost optimization, including token and caching strategies.
• Experience with Python, Java, C#, JavaScript, or SQL.
• Experience building and deploying applications.
• Knowledge of cloud platforms, containers, and CI/CD.
• Understanding of SDLC, APIs, and system architecture.
• Knowledge of databases and data integration.
• Understanding of LLM fundamentals and token behavior.
• Experience with LLMOps/MLOps, including versioning and experiment tracking.
• Experience with prompt engineering techniques.
• Experience with RAG pipelines, including embeddings and vector search.
• Familiarity with evaluation metrics, including accuracy and hallucination risk.
• Knowledge of GenAI debugging and safety mechanisms.
• Knowledge of deployment governance, including access control and compliance.
• Experience with observability, including logging, tracing, and monitoring.
• Experience with Azure, AWS, or GCP.
• Strong communication and requirements-gathering skills.

Nice To Haves

• Experience with model orchestration, including multi-step workflows and agents.
• Experience with LangChain, Semantic Kernel, or AutoGen.
• Experience designing embeddings and semantic search solutions.
• Experience with experimentation and A/B testing of prompts and models.
• Experience with conversational UX and human-AI interaction design.
• Experience with incident handling, including retries and graceful degradation.

Responsibilities

• Develop and modify application modules, including GenAI components.
• Build prompt workflows, retrieval layers, APIs, and cloud services.
• Troubleshoot production issues, including latency, hallucinations, and errors.
• Provide Level II production support for deployed systems.
• Design components, including LLM integrations and RAG pipelines.
• Implement CI/CD pipelines, containerization, and release processes.
• Develop RAG pipelines with embeddings, chunking, and vector search.
• Apply prompt engineering techniques, including few-shot prompting and structured outputs.
• Evaluate models for accuracy, relevance, and hallucination risk.
• Implement safety guardrails, including PII protection and prompt-injection defense.
• Execute testing, including unit, integration, and GenAI evaluation testing.
• Monitor production systems for latency, cost, usage, and errors.
• Support incident management with fallback and recovery strategies.

Benefits

• group health insurance benefits (medical, vision, dental)
• FSA and HSA healthcare accounts
• life and accident insurance
• adoption and fertility assistance
• paid parental leave of up to 6 weeks
• short/long term disability
• paid time off for vacation, personal needs, and sick time (up to 17 days per calendar year)
• up to 11 paid holidays per calendar year
• 401(k) savings and investment plan or deferred compensation plan (if eligible), with an employer match of 100% on the first 3% of your contributions for eligible employees

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed