Senior Software Engineer

This is a fully remote position, open to applicants in Latin America.

📋 Description

• Design, develop, and maintain customer-facing AI platform services and product features primarily using Python, while also integrating with PHP and Java systems as needed.

• Create and enhance agentic harnesses, which include agent runtimes, workflow orchestration, tool execution, state management, recovery paths, and evaluation hooks.

• Integrate agents and LLM-powered workflows into production systems with a strong focus on reliability, correctness, latency, scalability, and cost-effectiveness.

• Assess models and providers for specific product use cases, utilizing clear success criteria and abstractions to maintain platform flexibility as the AI landscape evolves.

• Take ownership of evaluation, tracing, observability, and quality feedback loops for AI features, enabling the team to identify regressions, comprehend behavior, and facilitate continuous improvement.

• Produce clean, thoroughly tested, and well-documented code while advocating for engineering best practices, test automation, maintainability, and operational excellence.

• Collaborate with product, design, data, security, and engineering teams to transform ambiguous AI product opportunities into dependable customer-facing features.

• Develop, troubleshoot, and manage services that interact with PostgreSQL, SQS, gRPC, and REST APIs, including data models, event streams, service contracts, and versioning.

• Serve as a senior individual contributor through technical leadership, providing architecture input, engaging in pair programming, conducting code reviews, and offering mentorship.

⛳️ Requirements

• Over 5 years of software engineering experience in building, deploying, and maintaining production systems.

• Strong expertise in Python within production settings, encompassing APIs, services, testing, debugging, and operational ownership.

• Practical experience in building, integrating, or evaluating agentic systems, agent harnesses, tool orchestration, or LLM-powered workflows.

• Familiarity with agentic frameworks and tools such as LangChain, LangSmith, LangGraph, or similar platforms (e.g., PydanticAI, CrewAI).

• Experience with MCP, vector databases, retrieval patterns, RAG architectures, or AI evaluation platforms.

• Comfortable working across a polyglot stack, particularly in contributing to or integrating with PHP and Java services as required by the product.

• Knowledge of prompt and version management, guardrails, tracing, LLM observability, cost and latency optimization, or human-in-the-loop workflows.

• Experience with cloud infrastructure and containerization technologies like Docker, Kubernetes, and AWS, along with experience working in remote-first, globally distributed teams.

• Proficiency in API-driven design, distributed systems, data modeling, and establishing reliable service boundaries.

• Strong understanding of software best practices, design patterns, performance considerations, security-focused development, and testing across unit, integration, and end-to-end levels.

• Excellent problem-solving and debugging abilities, particularly in complex systems with uncertain or probabilistic behavior.

• Strong product sense, customer empathy, effective communication, teamwork, ownership, and time management skills.

• Business-level English fluency, both verbal and written.

• Candidates must currently be authorized to work in the location where the position is based without requiring visa sponsorship.

🏝️ Benefits

• Remote First, Remote Always.

• PTO in accordance with local labor requirements.

• Fully Paid Parental Leave.

• Home office stipend based on country of residency.

• Professional development courses available through Cloudbeds University.

• Access to professional development opportunities, including manager training, upskilling, and knowledge transfer.