Senior Software Engineer (Knowledge Engine)

Senior Software Engineer, AI Search & Retrieval

Location: Remote (US, Pacific through Eastern time zones)
Employment: Full-time
Compensation: $175,000–$195,000 base + equity
Company: Growing AI Software Company

About the Opportunity

Fuel Talent is partnering with an innovative, venture-backed technology company building next-generation enterprise software powered by AI. The team is developing sophisticated solutions that help organizations process complex information, improve knowledge accessibility, and power intelligent applications through advanced AI technologies.

We're looking for a Senior Software Engineer, AI Search & Retrieval to help build and scale the backend systems powering intelligent document processing, knowledge management, and information retrieval.

This is a hands-on engineering role with significant ownership from day one. You'll work closely with engineering leadership to build production-grade Python services, develop scalable retrieval systems, and improve the accuracy, reliability, and performance of AI-powered applications.

The ideal candidate brings strong backend engineering experience, has built and measured production search or retrieval systems, and understands how to combine traditional search, vector retrieval, and knowledge graphs to deliver accurate, measurable results.

What You'll Do

• Design, build, and maintain production-grade Python services supporting document ingestion, processing, indexing, and retrieval.

• Develop scalable pipelines for processing large documents, structured and unstructured data, and complex content.

• Build and optimize search and retrieval systems using a combination of vector search, graph databases, and keyword-based approaches.

• Develop and maintain knowledge graph models, graph queries, and integrations with embedding and vector storage technologies.

• Implement and tune retrieval and ranking strategies to improve relevance, accuracy, and overall system performance.

• Establish measurable evaluation frameworks for search and retrieval quality, including precision, recall, and answer accuracy.

• Benchmark and optimize retrieval approaches to ensure reliable performance across different data types and use cases.

• Implement security measures to protect document ingestion and retrieval pipelines from malicious or untrusted content.

• Deploy, monitor, and troubleshoot production services running on Kubernetes.

• Collaborate with engineering teams to evaluate emerging retrieval technologies and incorporate proven approaches into production.

• Contribute to backend architecture, APIs, and distributed systems supporting the broader platform.

• Maintain high standards for code quality, observability, documentation, and secure software development.

What Success Looks Like

Within your first six months, you'll have:

• Taken ownership of reliable, scalable document ingestion and retrieval services.

• Improved retrieval accuracy and performance through measurable evaluations and benchmarking.

• Built or enhanced production search capabilities combining multiple retrieval techniques.

• Established repeatable processes for monitoring retrieval quality, diagnosing failures, and improving system reliability.

• Demonstrated independent ownership of Python services running in production.

• Contributed meaningful improvements to the broader engineering platform.

What We're Looking For

• 5+ years of professional software engineering experience, with significant hands-on backend development.

• Strong proficiency in Python, including building and maintaining production backend services.

• Proven experience designing, building, and operating production search or retrieval pipelines.

• Hands-on experience with graph databases, including writing and optimizing graph queries using Cypher, SPARQL, or similar query languages.

• Experience with RAG (Retrieval-Augmented Generation), vector databases, embeddings, and information retrieval techniques.

• Demonstrated ability to evaluate retrieval performance using measurable metrics such as precision, recall, relevance, or answer quality.

• Strong understanding of distributed systems, APIs, data processing, and production software architecture.

• Experience deploying and operating applications on Kubernetes, including troubleshooting production incidents.

• Hands-on experience with AWS or Azure cloud infrastructure and services.

• Familiarity with secure software development practices, including automated testing, code review, and security scanning.

• Experience processing structured and unstructured information at scale.

• Comfortable working within established architectural direction while taking ownership of implementation and delivery.

• Strong communication skills and the ability to collaborate across engineering disciplines.

Nice to Have

• Experience with search relevance engineering, ranking systems, or information retrieval optimization.

• Familiarity with Neo4j, RDF-based graph databases, or similar knowledge graph technologies.

• Experience with hybrid retrieval strategies combining semantic, graph-based, and keyword search.

• Knowledge of ontologies, entity relationships, and graph-based data modeling.

• Experience processing complex documents, PDFs, tables, or large-scale unstructured datasets.

• Exposure to AI-powered enterprise applications or knowledge management platforms.

• Experience working with security-sensitive information or applications requiring strong auditability.

• Background working at an early-stage startup or AI infrastructure company.

Why This Opportunity?

• High ownership: Take responsibility for meaningful backend and AI infrastructure initiatives from day one.

• Modern AI technologies: Build real production retrieval systems using Python, knowledge graphs, and advanced search techniques.

• Technical depth: Work across distributed systems, Kubernetes, cloud infrastructure, and AI-powered applications.

• Early-stage impact: Help shape the engineering foundations of a growing AI company.

• Collaborative environment: Work directly with experienced engineering leaders on technically challenging problems.

Additional Details

This is a full-time, remote opportunity for candidates based in the United States, working within Pacific through Eastern time zones. Candidates must have existing US work authorization without requiring visa sponsorship.