Senior Applied ML Engineer (Agentic Search)
Core
Design, train, and deploy ML models for retrieval, reranking, and indexing at scale to power an agent-native search platform for AI systems.
Role type
Senior Applied ML Engineer (Search & Retrieval)
Builds
Production ML models for retrieval, ranking, and indexing used 24x7 by AI systems.
Domain
Cloud Infrastructure / AI / Search & Information Retrieval
Deliverable
production ML models
Required skills
Python, Go, C++, production ML deployment, retrieval/ranking algorithms, deep learning, large-scale data systems, evaluation framework design, system optimization (latency/cost), LLM-integrated systems
Preferred skills
search systems, embeddings, transformers, NLP, open-source contributions, competitive ML
Technologies
Python, Go, C++, transformers, LLMs
Responsibilities
Design, train, and deploy ML models for retrieval, reranking, and search relevance; Build and optimise embedding-based indexing and large-scale retrieval systems; Develop models supporting crawling, data selection, and content understanding; Define and improve quality metrics for agent-native search and build evaluation pipelines; Work on systems operating at very large scale, including high-throughput query workloads; Collaborate closely with engineering teams to integrate ML models into production services; Analyse performance trade-offs across latency, quality, and cost; Experiment with and apply state-of-the-art techniques in search, retrieval, and LLM-integrated systems; Contribute to product and architectural decisions in a fast-moving environment
Seniority
Senior, hands-on IC
