Machine Learning Search Engineer

Apt is building the next generation of intelligent product search systems that understand user intent and learn from behavior. As a Senior Python Engineer on the ML/AI Search team, you will architect and build backend services that power product discovery for millions of industrial buyers, focusing on scalable retrieval pipelines, real-time inference, and APIs.

Responsibilities:

• Design, develop, and deploy end‑to‑end Python services—from retrieval and ranking pipelines to customer‑facing APIs
• Integrate ML inference pipelines: embeddings, transformer models, LLM‑powered query understanding, and reranking
• Build event‑driven, real‑time architectures using GCP (Cloud Run, Pub/Sub, GKE, Cloud Functions)
• Own your services in production: testing, observability, monitoring, and on‑call
• Partner with Search and ML Architects to build hybrid retrieval systems combining keyword search, vector similarity, and ML reranking
• Maintain Elasticsearch indexing pipelines, query services, and relevance‑tuning tools
• Integrate vector databases (Pinecone, Weaviate, FAISS, etc.) into retrieval workflows
• Instrument pipelines with meaningful metrics (CTR, zero‑result rate, latency) to drive A/B experimentation
• Champion CI/CD, observability, testing, and infrastructure‑as‑code
• Lead design discussions and translate product requirements into clean, scalable solutions
• Participate in code reviews and knowledge‑sharing to elevate the entire team

Requirements:

• 4+ years of professional backend or full‑stack engineering experience with a strong Python focus
• Experience building and deploying cloud‑native applications (GCP preferred; AWS/Azure welcome)
• Hands‑on experience with microservices, REST/gRPC APIs, Docker, Kubernetes, and serverless patterns
• Strong grounding in software design principles and clean engineering practices
• Excellent communication skills and comfort working with ML engineers, architects, and product teams
• Willingness to use AI tools to accelerate development
• Experience with search platforms (Elasticsearch, OpenSearch, Solr, Algolia)
• Familiarity with vector search concepts and tools (embeddings, ANN, FAISS, Pinecone, Weaviate)
• Exposure to ML/AI workflows: RAG pipelines, LLM integration, prompt engineering, fine‑tuning
• Experience with AI orchestration frameworks (LangChain, LangGraph, Google ADK)
• Infrastructure‑as‑code (Terraform, Pulumi) and mature CI/CD pipeline ownership