Description
We are seeking a Senior Applied AI Engineer to join our team at Paradox, part of Workday. As a Senior Applied AI Engineer, you will lead the bridge between cutting-edge AI capabilities and production-grade software. You will design, build, and optimize the intelligent systems, agentic workflows, and LLM-driven architectures that power Paradox's conversational products.
In this role, you will:
- Design & Scale AI Systems: Architect and deploy high-performance LLM orchestration systems, agentic workflows, retrieval-augmented generation (RAG) pipelines, and AI microservices.
- Bridge AI Research & Production: Transform frontier LLM research, foundation models, and generative techniques into robust, production-ready features with high availability and low latency.
- LLM Evaluation & Guardrails: Design and implement automated LLM evaluation (evals) frameworks, benchmark suites, and guardrail policies to continuously measure accuracy, reduce hallucinations, and ensure safety across product flows.
- Optimize Performance & Cost: Lead latency, throughput, and token-cost optimization strategies across commercial APIs and open-source models.
- Set AI Engineering Standards: Elevate software craftsmanship across the team through architectural reviews, code quality, and LLMOps best practices, utilizing the latest AI tools.
- Drive Product Innovation: Collaborate closely with product and engineering teams to translate complex human resource and conversational challenges into intelligent software solutions.
Basic Qualifications:
- Applied Generative AI: Proven track record of shipping complex LLM systems to production (e.g., Multi-agent architectures, RAG systems, tool/function calling, complex dialogue managers) coupled with a passion for continuous AI innovation.
- 5+ years of hands-on software development experience, focusing on building complex, distributed systems.
- System Architecture & Cloud: Strong system design skills in cloud-native environments (AWS/GCP), containerization, and modern CI/CD automation.
- Engineering Quality for AI: Deep understanding of testing non-deterministic AI systems (eval-driven development, deterministic regression testing, automated benchmarking).
- Technical Leadership: Proven experience leading architectural designs, driving cross-functional alignment, and mentoring engineers in AI engineering principles.
- Fluent English: High proficiency in both written and verbal communication.
- Work Authorization: Authorization to work in Israel.
Preferred Qualifications:
- Python Expertise: Deep proficiency in Python and modern backend framework development, with strong API design and asynchronous programming skills.
- Vector Search & AI Infrastructure: Hands-on experience with Vector Databases (e.g., Pinecone, Qdrant, Milvus, pgvector) and modern orchestration frameworks (e.g., LangChain, LlamaIndex, AutoGen/CrewAI).
- Model Customization & Fine-Tuning: Practical experience with model fine-tuning techniques (e.g., LoRA, QLoRA, SFT, DPO/RLHF) and dataset curation.
- LLMOps & Observability: Hands-on experience with LLM tracing and observability stacks (e.g., LangSmith, Phoenix, Arize, Weights & Biases).
- Inference & Serving: Familiarity with LLM serving engines and frameworks (e.g., vLLM, TensorRT-LLM, Ollama).
- Domain Experience: Background in Conversational AI, Dialogue Management, or Recruitment/HR tech automation.
- Data Science/ML Foundation: Formal background or practical grounding in NLP, Machine Learning, or Data Engineering.