Senior Software Engineer, Python, AI Platform

This is a fully remote position, open to applicants in United States.

📋 Description

• Lead the backend development for AI workflows utilizing Python and FastAPI.

• Implement LLM integrations in production, encompassing Bedrock utilization, quotas, retries, failover mechanisms, cost controls, model configuration, and approval constraints.

• Create secure and compliant systems that ensure tenant isolation, auditability, observability, and traceable AI outputs.

• Enhance enterprise platform capabilities through asynchronous job orchestration, performance optimization, and data-layer enhancements.

• Contribute to multi-tenant services, role-based access control (RBAC), single sign-on (SSO) integration, and administrative/reporting functionalities.

• Boost reliability through monitoring, tracing, alerting, and operational tools.

• Design real-time event delivery and publish/subscribe patterns for workflow states, notifications, and agent feedback.

• Collaborate on shared services, platform architecture, and integration boundaries.

• Transform evolving product and non-functional requirements into technical solutions in partnership with product, architecture, legal, and security stakeholders.

• Promote strong typing, automated testing, continuous integration, and schema-driven API contracts.

⛳️ Requirements

• Over 7 years of professional software development experience, including a minimum of 5 years developing Python services in a production environment.

• Expertise in Python backend engineering, including APIs, asynchronous processing, background jobs, and workflow orchestration.

• Experience with AWS cloud-native backend solutions.

• Demonstrated experience in production distributed systems with a focus on reliability, observability, retries, throughput, failure management, and performance optimization.

• Strong knowledge of PostgreSQL and large-scale data processing, including indexing, query optimization, and balancing batch/stream tradeoffs.

• Required familiarity with retrieval-augmented generation (RAG), vector search, and embedding-based systems.

• Experience in multi-tenant systems, RBAC, audit logging, secure data management, and regulated environments.

• Practical experience in building LLM-driven workflows, including tool invocation, state machines, human-in-the-loop approvals, checkpoint/resume capabilities, and multi-step orchestration.

• Familiarity with LangGraph or similar technologies.

• Experience in prompt engineering, evaluation design, and LLM cost optimization.

• Experience collaborating with AI-native engineering teams.

• A product-oriented mindset with the ability to make pragmatic, customer-focused tradeoffs.

• Strong advantages include knowledge of Bedrock, OpenAI, Anthropic, LangChain/LangGraph, SSO/SAML/OIDC, graph-shaped data, entity resolution, OpenTelemetry, Terraform, feature flags, canary deployments, and release strategies.

🏝️ Benefits

• Applicable bonus programs discussed during the recruiting process.

• Opportunities for professional development.

• A diverse and inclusive culture.

• A collaboration-focused work environment.