Job Url: https://www.linkedin.com/jobs/search/?currentJobId=4361982174&distance=25&f_TPR=r86400&f_WT=2&geoId=103644278&keywords=software%20engineer&origin=JOB_SEARCH_PAGE_JOB_FILTER&refresh=true Job Description: Senior AI Engineer Inkwell · United States (Remote) Easy Apply Save Save Senior AI Engineer at Inkwell Show more options Your profile is missing required qualifications Show match details Help me update my profile BETA Is this information helpful? Get personalized tips to stand out to hirers Find jobs where you’re a top applicant and tailor your resume with the help of AI. Try Premium for PKR0 About the job About the role We’re hiring a full-time Senior AI Engineer to help build and scale our core product, with deep ownership across AI systems, platforms, features, and senior-level contributions to backend, infrastructure, and system architecture. This is a hands-on role for an experienced engineer who operates with a high degree of autonomy: you can take ambiguous problems, make sound technical decisions, solicit feedback and deliver production-quality systems. You’ll work closely with the ML Lead as a trusted senior partner, contributing meaningfully to the company’s direction while owning major areas end-to-end.What you’ll do Own and ship AI systems, platforms and components to production: design, implement, test, deploy, and operate LLM-powered workflows (agents, tool calling, RAG, evaluation, guardrails) with accountability for quality and reliability. Take ownership beyond AI features: lead vertical development and integration across backend APIs, data pipelines, integrations, performance optimization, and system reliability. Contribute to system architecture: help define and evolve service boundaries, data models, and deployment patterns; improve modularity, scalability, and maintainability. Drive AI quality and robustness: implement and maintain evaluation harnesses, regression tests, prompt/model versioning, routing and fallback strategies, and cost/latency optimizations. Work deeply with real-world data: build and improve ingestion pipelines, chunking and embedding strategies, search relevance tuning, structured extraction, and privacy-aware data handling. Lead complex problem-solving: investigate and resolve production issues, debug hard technical problems, and reduce operational risk through better design and tooling. Collaborate cross-functionally: work closely with product and engineering partners to translate product needs into clear technical plans and execute effectively. What we’re looking for Must-have 6+ years of professional software engineering experience, operating at a senior level. Strong backend engineering skills (APIs, data stores, production systems, distributed systems fundamentals, debugging). Hands-on experience building with modern LLM stacks (e.g., Anthropic, OpenAI/Azure OpenAI or similar), including MCP, tool/function calling, structured outputs, RAG, prompt design, and evaluation. Strong software engineering fundamentals: clean code, testing discipline, observability, and ownership of production systems. High ownership and judgment: able to independently drive work forward, communicate clearly, and make sound technical decisions. Nice-to-have Experience with vector search and retrieval systems (Elasticsearch, OpenSearch, Pinecone, Weaviate, etc.). Experience with GCP (Cloud Run, queues, object storage, CI/CD, monitoring). Experience with distributed, event-driven, or workflow-based systems. Familiarity with security and privacy considerations for AI systems (PII handling, redaction, access control, auditability). Front-end familiarity (React) is a plus, but not required. GIS data handling experience is a plus, but not required. Tech stack LLMs: OpenAI / Azure OpenAI, tool calling, evaluation harnesses Backend: Node.js and/or Python (FastAPI), REST APIs Data: Postgres, Elasticsearch / vector search, GIS Infra: Google Cloud, containerized services Best of breed coding tooling: Claude Code, Codex, Cursor, GitHub, CI/CD, observability and logging What success looks like (first 60–90 days) You independently own and ship meaningful AI and backend capabilities with minimal oversight. You improve system quality and reliability through better architecture, testing, evaluation, and monitoring. You find and optimize inefficiencies in team's development process and work with leadership to improve DORA metrics You take long term ownership of core areas, reducing single points of failure through strong execution and documentation. Why this role High ownership and direct impact on core product capabilities. Close collaboration with experienced technical leadership in a small, senior engineering team. A mix of AI engineering and real-world software engineering: shipping, scaling, and operating production systems.