ML Search Engineer

Summary

Seneca Resources is a staffing and consulting firm that partners with clients to provide impactful career opportunities. They are seeking a Full Stack Engineer III to build AI-powered search experiences, develop modern full-stack applications, and advance search and AI infrastructure, all while contributing to engineering excellence.

Responsibilities

• Design, develop, and deploy scalable Python services that power search retrieval, ranking, recommendation, and discovery experiences
• Build and integrate machine learning inference pipelines, including embeddings, transformer models, query understanding, reranking services, and LLM-powered features
• Develop robust APIs and microservices that support high-volume search workloads and customer-facing applications
• Collaborate with product, engineering, and AI teams to translate business goals into impactful search solutions
• Continuously improve search relevance, performance, and user engagement through experimentation and data-driven decision making
• Build responsive, accessible, and performant user interfaces using React and modern JavaScript frameworks
• Create reusable frontend components and establish engineering standards that improve consistency and developer productivity
• Partner with UX and Product teams to transform wireframes and Figma designs into intuitive customer experiences
• Contribute to frontend architecture decisions that support long-term scalability and maintainability
• Implement hybrid search architectures that combine keyword search, vector search, semantic retrieval, and AI-powered ranking
• Build and maintain Elasticsearch/OpenSearch indexing pipelines, query services, and relevance tuning capabilities
• Integrate vector databases and retrieval systems such as Pinecone, Weaviate, FAISS, or similar technologies
• Develop and optimize Retrieval-Augmented Generation (RAG) and LLM-powered search workflows
• Instrument search systems with meaningful metrics, including click-through rate, latency, engagement, and zero-result rates to drive ongoing optimization
• Develop event-driven, distributed systems using Google Cloud Platform (GCP) services such as Cloud Run, GKE, Pub/Sub, and Cloud Functions
• Deploy, monitor, and maintain production services using modern DevOps and observability practices
• Own service reliability through testing, monitoring, troubleshooting, and operational excellence
• Participate in architecture discussions, technical design reviews, and code reviews
• Mentor peers through collaboration and knowledge sharing
• Champion engineering best practices, software craftsmanship, and continuous improvement

Skills

• 4+ years of professional experience in Full Stack Engineering, Backend Engineering, or Software Development
• Strong hands-on experience building applications with Python and React
• Experience with modern frontend frameworks such as Next.js, Remix, Vite, Gatsby, or similar technologies
• Proven experience building and supporting scalable microservices, REST APIs, and/or gRPC services
• Experience deploying and operating cloud-native applications in GCP, AWS, or Azure
• Experience with Docker, containerized applications, and serverless architectures
• Strong understanding of software design patterns, SOLID principles, testing strategies, and maintainable code practices
• Experience working with relational and NoSQL databases such as PostgreSQL, MySQL, Oracle, MongoDB, DynamoDB, or similar platforms
• Strong communication skills with the ability to collaborate effectively across engineering, product, and architecture teams
• Comfortable leveraging AI-assisted development tools to improve productivity and quality
• Elasticsearch, OpenSearch, Solr, Algolia, or other enterprise search platforms
• Search relevance tuning, query optimization, indexing strategies, and ranking algorithms
• Large-scale search infrastructure and information retrieval systems
• Generative AI, Large Language Models (LLMs), and AI-powered search experiences
• Retrieval-Augmented Generation (RAG)
• Prompt engineering and LLM orchestration
• LangChain, LangGraph, Google ADK, or similar frameworks
• Machine learning model deployment and inference pipelines
• Embeddings and semantic search architectures
• Approximate Nearest Neighbor (ANN) search
• Pinecone, Weaviate, FAISS, Milvus, or similar vector database technologies
• Monorepo development environments
• Event-driven architectures
• Distributed systems at scale
• A/B testing and experimentation frameworks

Qualifications

Must Haves

• 4+ years of professional experience in Full Stack Engineering, Backend Engineering, or Software Development
• Strong hands-on experience building applications with Python and React
• Experience with modern frontend frameworks such as Next.js, Remix, Vite, Gatsby, or similar technologies
• Proven experience building and supporting scalable microservices, REST APIs, and/or gRPC services
• Experience deploying and operating cloud-native applications in GCP, AWS, or Azure
• Experience with Docker, containerized applications, and serverless architectures
• Strong understanding of software design patterns, SOLID principles, testing strategies, and maintainable code practices
• Experience working with relational and NoSQL databases such as PostgreSQL, MySQL, Oracle, MongoDB, DynamoDB, or similar platforms
• Strong communication skills with the ability to collaborate effectively across engineering, product, and architecture teams
• Comfortable leveraging AI-assisted development tools to improve productivity and quality

Nice to Haves

• Elasticsearch, OpenSearch, Solr, Algolia, or other enterprise search platforms
• Search relevance tuning, query optimization, indexing strategies, and ranking algorithms
• Large-scale search infrastructure and information retrieval systems
• Generative AI, Large Language Models (LLMs), and AI-powered search experiences
• Retrieval-Augmented Generation (RAG)
• Prompt engineering and LLM orchestration
• LangChain, LangGraph, Google ADK, or similar frameworks
• Machine learning model deployment and inference pipelines
• Embeddings and semantic search architectures
• Approximate Nearest Neighbor (ANN) search
• Pinecone, Weaviate, FAISS, Milvus, or similar vector database technologies
• Monorepo development environments
• Event-driven architectures
• Distributed systems at scale
• A/B testing and experimentation frameworks

Benefits

• Comprehensive health, dental, and vision coverage
• 401(k) retirement plans
• Support of a dedicated team who will advocate for you every step of the way