Senior Software Engineer (Python) - Remote

Mitratech

17h•Remote

About The Position

Join Mitratech’s Workforce Compliance Engineering team to build AI-first SaaS products. The role combines developing customer-facing AI capabilities—such as LLM-powered workflows, retrieval over compliance content, and agents that take action within products—with helping lead an agentic, pipeline-driven approach to software development. In that approach, AI coding agents plan, write, test, and review code under strong engineering oversight. The team’s engineering standards emphasize quality and low escaped-defect rates, thorough testing with a focus on unit test coverage and Cypress automation, security scanning and verification, scalability on AWS, and measurable accuracy for AI features. The position offers the opportunity to architect solutions to complex problems and deliver product features where clean code and trustworthy AI matter. The engineer will decompose product goals into clear tasks and specifications, develop AI-enabled CI/CD pipelines and agent instructions, review human- and AI-generated code, and provide architectural oversight. The role also includes contributing to domain models and technical documentation, writing secure code, participating in an on-call rotation, helping teammates resolve difficult problems, and mentoring colleagues in effective and responsible use of AI agents.

Requirements

Bachelor’s degree or equivalent experience; the posting prefers an emphasis in engineering, data science, computer science, or information systems.
At least 5 years of software engineering experience developing SaaS applications.
Strong hands-on experience with Python, React, and AWS, including Lambda and DynamoDB.
Hands-on experience with LLM application patterns, including prompt design, embeddings and vector search/RAG, tool or function calling, structured outputs, and agent orchestration.
Demonstrated experience delivering software with AI coding agents such as Claude Code, Devin, or Codex as a core part of the workflow, including integrating agents into CI/CD pipelines with automated quality gates.
Experience designing evaluation and testing strategies for non-deterministic systems, and sound judgment about when AI is and is not an appropriate solution.
Strong fundamentals in system design, API security, automated testing, and multi-tenant SaaS architecture.
Clear, precise written communication, including specifications and documentation that people and AI agents can act on.

Nice To Haves

Experience with managed model platforms and provider APIs such as Amazon Bedrock, Anthropic, or OpenAI, and with agent frameworks or SDKs.
Experience shipping at least one AI/LLM-powered feature in a SaaS product and supporting it after launch through monitoring, evaluation, and iteration based on real usage.
Experience building MCP servers or other tool integrations for AI agents.
Background in regulated domains such as HR, legal, risk, or compliance, and familiarity with data privacy and security standards such as SOC 2, GDPR, or CCPA.
Familiarity with AI risk and governance practices such as NIST AI RMF or the OWASP Top 10 for LLM Applications.
Experience with spec-driven development.

Responsibilities

Break down high-level product goals into modular engineering tasks with specifications and acceptance criteria suitable for engineers and AI coding agents.
Develop and optimize CI/CD pipelines that incorporate AI agents for code generation, automated testing, and code review, with guardrails, quality gates, and human approval points.
Design, test, and improve instructions, prompts, specifications, and repository context—including agent instruction files, reusable skills, and MCP tools—to improve AI-agent output.
Review human- and AI-generated code for quality, security, scalability, and alignment with domain requirements.
Ensure designs created by engineers and AI tools follow architectural best practices, including modularity and bounded contexts.
Contribute to domain models, technical documentation, and internal knowledge bases that support AI-agent performance and team work.
Write secure code and avoid OWASP vulnerabilities, including those identified in the OWASP Top 10 for LLM Applications; secure APIs and sessions and validate data appropriately.
Participate in an on-call rotation and respond promptly to production issues, including AI feature degradations, to remediate them rapidly.
Help teammates resolve complex problems and consider design and architecture challenges; be available and responsive.
Mentor others and foster an engineering culture based on trust, accountability, character, and honesty, including coaching teammates on responsible and effective AI-agent use.
Seek feedback and deliver tactful, empathetic constructive criticism, including through code reviews, and mentor without ego.