Our investors include Softbank, Amazon, Alibaba, Verizon, NTT DoCoMo, Qualcomm and PepsiCo.
We seek an experienced individual contributor (IC) with potential for future team leadership, specializing in deploying generative AI applications in production at scale. The role focuses heavily on robust production methodologies, including monitoring, evaluation, failure analysis, and resilience.
Reporting to the Director, you'll shape Wiliots AI roadmap for internal tools, customer solutions, and external SDKs.
Responsibilities
Develop, deploy, and scale robust generative AI applications (agents, copilots, intelligent interfaces).
Design and maintain scalable, secure architectures for LLM-driven services.
Own full AI lifecycle: prompt engineering, embedding models, retrieval systems (vector DBs), real-time monitoring, observability, and failure mitigation.
Collaborate cross-functionally with software engineers, product teams, and business stakeholders.
Translate ambient IoT data into practical AI-driven experiences (logistics, sustainability, inventory management).
Contribute to developing SDKs/APIs for external AI workflows.
Experiment with advanced GenAI techniques (LLMs, hybrid search, multimodal).
Proven experience deploying generative AI solutions to production at scale.
Extensive hands-on expertise in frameworks including:
RAG Pipelines: Chunking (token, semantic, markdown-aware), embedding models (OpenAI, Cohere, HuggingFace), vector DBs (Pinecone, Weaviate, FAISS), retrieval evaluation (Precision@k, RAGAS), hybrid search.
LLM orchestration: LangChain, LlamaIndex, Semantic Kernel, Haystack, tool/function calling, memory management.
Evaluation & monitoring: Prompt versioning, grounding evaluation, LLM-as-judge, LangSmith, TruLens, failure analysis (hallucination, context overflow, function calls), real-time observability.
Resilience: Prompt injection prevention, output validation (JSON schema, type checking), fallback logic.
Deployment: Caching strategies, multi-model routing, cost-performance optimization.
Strong software engineering skills: Python, FastAPI, Docker, Kubernetes.
Proven ability to manage real-time IoT or streaming data integration.
Excellent communication skills with technical and non-technical teams.
Comfort in fast-paced, agile environments.
Advantages
Background in IoT or ambient sensing.
Familiarity with advanced orchestration frameworks or autonomous agent systems (AutoGPT, CrewAI, LangGraph).
Prior experience building AI SDKs/developer platforms.
Background in NLP, multimodal AI, or knowledge graphs.
Good understanding (not necessarily expert-level) of data science concepts.
