Senior Software Engineer (Python) - Remote

Mitratech; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

Join Mitratech's Workforce Compliance Engineering team, building AI-first SaaS products that power compliance workflows. You will design and implement LLM-powered features, retrieval over content, and agents that write and review code under strong engineering oversight.

You will lead pipeline-driven development, CI/CD with AI agents, ensure security and quality, and collaborate across teams to deliver reliable, scalable solutions used by customers worldwide.

Qualifications

• Bachelor's degree or equivalent experience in engineering, data science, or CS.
• 5+ years of SaaS software engineering experience.
• Hands-on with Python, React, and AWS.
• Experience with AI coding agents and CI/CD pipelines.
• Familiar with prompt design, embeddings, vector search, and RAG.

Responsibilities

• Break down high-level product goals into modular engineering tasks with AI agents.
• Develop and optimize CI/CD pipelines with AI agents for code generation, testing, and review.
• Design and test structured instructions, prompts, and repository context for AI agents.
• Conduct in-depth reviews of human and AI-generated code for quality and security.
• Ensure architectural adherence, modularity, and domain-aligned design.

Skills

Python

React

AWS

LLM patterns

Agent orchestration

CI/CD pipelines

Embeddings

Vector search

Tool calling

Structured outputs

Education

Bachelor's degree

Tools

Claude Code

Devin

Codex

Amazon Bedrock

OpenAI

Job description

At Mitratech, we are a team of innovators focused on building world-class products that simplify operations in the Legal, Risk, Compliance, and HR functions. We are a close-knit, globally dispersed team that thrives in an ecosystem that supports individual excellence and takes pride in its diverse and inclusive work culture centered around great people practices, learning opportunities, and having fun! Our culture is the ideal blend of entrepreneurial spirit and enterprise investment, enabling the chance to move at a rapid pace with some of the most complex, leading-edge technologies available. For over 35 years, the experts at Mitratech have been focused on solving the complex needs. Today, we serve 20,000 client companies of all sizes globally, representing 30% of the Fortune 500 and over 500,000 users in over 160 countries. As we continue to grow, we’re always looking for resourceful, enthusiastic, and fresh perspectives. Join our global team and see what makes Mitratech a truly exceptional place to work!

Job Overview:

You’ll be joining our Mitratech Workforce Compliance Engineering team, building AI-first SaaS products. This role sits at the intersection of two disciplines. First, you’ll build the AI features our customers use every day: LLM-powered workflows, retrieval over compliance content, and agents that take action inside our products. Second, you’ll help lead how we build software, using agentic, pipeline-driven development in which AI coding agents plan, write, test, and review code under strong engineering oversight. We hold both to the same bar: high quality (low escaped defects), well tested (Cypress automation framework with focus on unit test coverage), secure (scanned and verified), scalable (AWS, but hardware isn’t the answer), and measurably accurate when AI is involved. This is a great opportunity to join a growing company, be part of an excellent team, architect solutions to complex problems, and deliver valuable features where clean code, and trustworthy AI, matter.

Essential Duties & Responsibilities:

Agentic, Pipeline-Driven Development System Design & Task Decomposition: Break down high-level product goals into well-defined, modular engineering tasks with clear specifications and acceptance criteria that can be executed by both engineers and AI coding agents.

Agentic Development Pipelines: Develop and optimize CI/CD pipelines that incorporate AI agents for code generation, automated testing, and intelligent code review, with guardrails, quality gates, and clear human approval points.

Specification & Context Engineering: Design and test structured instructions, prompts, specifications, and repository context (e.g., agent instruction files, reusable skills, MCP tools) that drive accurate, context-aligned output from AI agents, and measure and improve agent output over time.

Code Review & Validation: Conduct in-depth reviews of both human and AI-generated code, ensuring quality, security, scalability, and alignment with domain requirements.

Architectural Oversight: Ensure design plans created by both human engineers and AI tools adhere to architectural best practices with a focus on modularity, bounded contexts, etc.

Documentation and Domain Clarity: Contribute to the development of domain models, technical documentation, and internal knowledge bases that support AI agent performance and team activity.

Engineering Excellence & Teamwork

Write secure code. Avoid introducing an OWASP vulnerability, including those in the OWASP Top 10 for LLM Applications. Know how APIs are secured, sessions are handled, and data is validated properly. Serve in an on‑call rotation (DevOps philosophy where you will participate in ops) and respond promptly to any production issues, including AI feature degradations, to remediate rapidly. Be a teammate, help other teammates resolve complex problems or think through design/architecture challenges. Be available and responsive. Mentor others and foster an excellent engineering culture based in trust, accountability, character, and honesty, including coaching teammates on using AI agents effectively and responsibly. Seek feedback and deliver constructive criticism (e.g., code reviews) in a tactful and empathetic manner; build others up and mentor without ego.

Your Qualifications:

Required Possess a bachelor’s degree, or equivalent experience. Emphasis in engineering, data science, computer science or information systems is preferred. Have a minimum of 5 years of software engineering experience developing SaaS applications, with strong hands‑on experience in our stack: Python, React, AWS (Lambda, DynamoDB). Hands‑on experience with LLM application patterns: prompt design, embeddings and vector search/RAG, tool/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 your workflow, including integrating agents into CI/CD pipelines with automated quality gates. Experience designing evaluation and testing strategies for non‑deterministic systems, and the judgment to decide when AI is, and is not, the right solution. Strong fundamentals in system design, API security, automated testing, and multi‑tenant SaaS architecture. Clear, precise written communication: specs and documentation that both people and AI agents can act on. Preferred Experience with managed model platforms and provider APIs (e.g., Amazon Bedrock, Anthropic, OpenAI) and agent frameworks or SDKs. Have shipped at least one AI/LLM‑powered feature to production in a SaaS product and supported it after launch (monitoring, evaluation, and iteration based on real usage). Experience building MCP servers or other tool integrations for AI agents. Background in regulated domains (HR, legal, risk, or compliance) and with data privacy and security standards (e.g., SOC 2, GDPR, CCPA). Familiarity with AI risk and governance practices (e.g., NIST AI RMF, OWASP Top 10 fo)