Principal Software Engineer (Python)

About the role

The hybrid-remote Principal Software Development Engineer leads the design, development, and testing of complex software systems and applications. This senior-level position is responsible for creating scalable, high-quality software solutions while providing technical leadership, driving engineering excellence, and providing mentorship to engineering teams.

Responsibilities

• Arcitect and Evolve the Semantic Layer: Lead the redesign and scaling of the existing Semantic Layer Web Service, transitioning it from a manual 130-attribute baseline to an automated, high-availability enterprise intelligence platform.
• Take the Team Anchor Role: Serve as the primary technical lead for the delivery team, owning the architectural vision for Knowledge Representation and Semantic Search while ensuring "fiduciary-grade" performance as the system scales to 1,000+ attributes.
• Implement Advanced Reasoning: Design and deploy Hybrid Graph/Vector search architectures (GraphRAG) to enable complex global reasoning across disparate enterprise data assets.
• Develop High-Performance AI Services: Utilize Git or similar, Unix command line, Python, FastAPI, FastMCP, and ADK to build and enhance robust backend services that bridge core enterprise data with Agentic AI.
• Model Optimization (LLM & SLM): Partner with the Data Science team to architect intelligent routing logic that leverages Small Language Models (SLMs) for high-speed classification/extraction and Large Language Models (LLMs) for complex synthesis.
• Automate Metadata Ingestion: Collaborate with the Knowledge Engineering team to build automated workflows for Ontology Management and Entity Linking, eliminating single-resource bottlenecks and manual curation constraints.
• Establish Systematic Evaluation: Collaborate with Knowledge Engineering and Data Science teams to replace "vibe checks" with rigorous automated testing frameworks, utilizing metrics like Faithfulness, Answer Relevance, and Context Precision (RAGAS) to ensure quality during rapid scaling.
• Conduct Expert Code Reviews: Ensure high code quality, adherence to AI engineering standards, and architectural integrity across the Python/AI stack.
• Drive Test-Driven Development (TDD): Implement rigorous TDD practices, writing comprehensive unit and integration tests to ensure the reliability of non-deterministic semantic pipelines.
• Utilize specialized algorithms for Entity Disambiguation and Ontology Evolution to solve complex knowledge-graph scaling and schema-drift challenges.
• Optimize Performance and Scalability: Independently plan and execute system optimizations to ensure the Semantic Layer remains performant under enterprise-scale loads and high-dimensional search requirements.
• Resolve Complex AI Issues: Resolve deep technical challenges related to model hallucinations, "Lost in the Middle" context window phenomena, and retrieval latency.
• Stay Updated on Emerging AI Trends: Monitor and provide recommendations on the rapidly evolving AI landscape, including SLM success areas, prompt engineering, and synthetic data generation.
• Mentor Senior & Junior Engineers: Act as a technical mentor and coach, sharing expertise in Python, Semantic AI, and Cloud Architecture to upskill the broader engineering organization.

Qualifications

• Education & Experience: Master’s or Bachelor’s degree in Computer Science, AI, or a related field, with 10+ years of professional software engineering experience.
• Expert Python/FastAPI Developer: Proven experience in designing, scaling, and maintaining existing production web services in an asynchronous Python environment.
• Semantic & Graph Expertise: Deep understanding of Knowledge Representation, Ontologies, and Graph Reasoning; experience taking "boutique" internal tools and turning them into high-availability platforms.
• Advanced RAG Knowledge: Professional experience with Vector Databases, Hybrid Search, and advanced retrieval strategies (e.g., Query Expansion, HyDE, and Reranking).
• AI Orchestration Mastery: Advanced proficiency in ADK or similar model abstraction tools, with a strong grasp of the operational trade-offs between LLMs and SLMs.
• Evaluation Rigor: Familiarity with AI evaluation frameworks (RAGAS, DeepEval) and the use of LLMs to generate synthetic testing suites for benchmarking.
• Analytical & Scale-Minded: Strong ability to apply complex data structures and algorithms to solve scaling bottlenecks and non-deterministic logic problems.
• Cloud Architecture: Experience deploying and managing scalable AI services in cloud environments (GCP, AWS, or Azure).
• Communication & Leadership: Excellent communication skills with a track record of leading high-performing engineering PODs and collaborating with cross-functional stakeholders.

Pay

Annual Pay Range: 154,600 - 180,000 USD

Schedule

Hybrid-Remote