
Senior AI Engineer, MapGPT
Posted 3 days ago

Posted 3 days ago
This is a fully remote position, open to applicants in United States.
• Define the behavior of products, measurement frameworks, and evaluation systems for non-deterministic behaviors.
• Develop hypotheses, establish accurate results, compile datasets, and regulate changes based on regression outcomes.
• Regularly assess APIs, SDKs, data representations, and reference applications from the perspective of end users.
• Detect misuse, integration anti-patterns, and deficiencies, propose solutions, and ensure their implementation.
• Take ownership of the MVP in alignment with an agreed-upon north star technical design.
• Balance the pursuit of technical excellence with delivering valuable increments.
• Construct data pipelines and tools for data ingestion, conflation, entity resolution, quality checks, and both batch and streaming jobs.
• Monitor and assess external datasets, models, and benchmarks derived from research and open-source initiatives.
• Determine the appropriate time to utilize existing solutions versus developing internal ones.
• Design feedback loops and instrument systems to facilitate reproducible failure contexts.
• Transform recurring failures into evaluation cases.
• Establish boundaries for model-tools and enhance model harnesses.
• Define model responsibilities, delegation, and state management.
• Improve latency and cost per request through streaming, partial results, caching, model routing, and prompt structuring.
• Develop internal CLI, MCP, and other tools for rapid iteration.
• Share reusable tools with other teams.
• Conduct code and design reviews.
• Mentor engineers in evaluation practices.
• Assist in resolving unresolved technical issues.
• Participate in a 24/7 on-call rotation to ensure system availability.
• Bachelor's Degree in a STEM field.
• Over 5 years of experience in software engineering.
• Proven ownership of production services, pipelines, or SDKs.
• At least 2 years of experience delivering LLM-backed features to actual users.
• Familiarity with systems that manage error budgets, on-call rotations, and customer-facing regressions.
• In-depth data engineering skills, including SQL and at least one distributed processing framework.
• Experience with data pipelines where incorrect records are more critical than processing speed.
• Proficiency in tool calling and agent orchestration, addressing stale context, hallucinated arguments, silent partial successes, and unbounded loops.
• Strong expertise in Python or TypeScript.
• Ability to read code in various programming languages comfortably.
• Direct experience or a profound understanding of evaluations for non-deterministic systems.
• Experience constructing datasets and pinpointing failures through evaluations.
• Practical knowledge of more than one agent harness.
• Experience in diagnosing latency within a distributed request path.
• Capability to navigate ambiguity and make judgments to deliver narrow, functional solutions.
• Involvement in an on-call rotation, including possible immediate responses outside of regular working hours and on weekends.
• Experience with geospatial data, routing, geocoding, POI or address data, OpenStreetMap, or conflating overlapping sources (nice to have).
• Experience in designing public APIs or SDKs (nice to have).
• Familiarity with building against MCP or similar tool transports (nice to have).
• Experience in conducting evaluations in CI (nice to have).
• Background in automotive, in-vehicle infotainment, CarPlay, or Android Auto (nice to have).
• Experience in voice pipelines including streaming ASR, TTS, barge-in, endpointing, or wake word (nice to have).
• Experience working under limited compute, offline, or intermittent connectivity (nice to have).
• Experience in managing a product through its initial external integrations (nice to have).
• Supportive health care.
• Parental leave.
• Flexible work arrangements.
• Opportunities for teaching and learning.
• Private medical coverage for you and your dependents.
• Generous maternity and paternity leave policies.
• Inclusive fertility support.
• Contributions to a Lifestyle Spending Account for health, wellness, and personal growth.
• Mental health support for you and your dependents.
• Flexible paid time away.
• Company holidays.
• Generous absence policies.
• Dedicated paid time for volunteering.
• Competitive retirement plans with matching contributions.
• Hybrid/remote work options.
Get handpicked remote jobs straight to your inbox weekly.