AI Engineer

Sr Security Analyst/Engineer
Job Description
Duties and Responsibilities
Job Title: Senior Agentic Platform Engineer (Python/ML)
Department: Research & Development
Prepared By: Razvan Dima
Reports To: Director of Innovation, Research & Development
Reviewed Date: July 2026
Approved By: Razvan Dima
A. Job Description Objective
We’re looking for an experienced Python + ML/Data Science engineer to join our agentic engineering team and help
build and support our agentic platform—a multi-tenant SaaS platform for building, deploying, and managing AI
agents and their associated toolkits/integrations. You will primarily deliver new capabilities in the platform backend,
the Agent API, and the agents themselves, while also raising the team’s maturity in agent design, evaluation, and
ML/DS-informed approaches.
This role is intended for someone who brings strong hands-on experience building agents in production and can help
accelerate internal capability building.
B. What You’ll Work On
Core engineering scope (hands-on):
➢ Platform backend feature development for agent lifecycle management (create/configure/test/deploy) and
platform services supporting multi-tenant isolation
➢ Agent API development (REST surface + workflows) including agent CRUD, configuration schema handling, and
orchestration-facing endpoints
➢ Custom agent packaging + validation workflows (e.g., zip packaging requirements, manifest validation key
process, and A2A protocol compliance)
➢ Runtime/deployment mechanics across local/container development and production hosting patterns (e.g.,
Docker-based workflows and AWS-hosted runtime patterns used by the platform)
Support & operational quality (shared ownership):
➢ Participate in supportability and debugging of agent behavior, tool execution, and platform/API issues (triage,
reproduction, root cause analysis, fixes)
➢ Strengthen testing strategy for agents and platform APIs, including building automated/unit tests and pragmatic
evaluation harnesses for agent behavior
C. Key Responsibilities
➢ Design and implement new backend capabilities in the platform aligned to the platform’s goals of enabling faster
iteration/release cycles
➢ Build and maintain production-grade Python services powering the Agent API and agent runtime workflows
➢ Develop and iterate on agents (simple/config-driven and custom/code-based), including prompt/systeminstruction design, tool usage patterns, and reliability improvements
➢ Establish or improve agent evaluation practices (repeatable tests, regression coverage, measurable quality
gates) suitable for frequent releases
➢ Collaborate closely with architects, platform engineers, QA, and support to ensure features are operable,
testable, and supportable
D. Required Qualifications
➢ Strong Python engineering experience delivering production systems (APIs/services, testing, packaging,
debugging)
➢ Demonstrated experience building AI agents (tool-using agents, multi-step reasoning workflows, orchestration
patterns, RAG/KB integration patterns)
Sr Security Analyst/Engineer
➢ Solid ML + Data Science background (model behavior, evaluation methods, experimentation discipline, datadriven iteration)
➢ Experience working with REST APIs, authentication/token-based access patterns, and service integration
boundaries
➢ Ability to operate in an engineering environment that requires security, governance, and controlled deployment
for code-based agents
E. Experience Requirements
➢ Minimum 5 years of professional software engineering experience with Python in production environments
➢ Minimum 3 years of hands-on experience with AI/ML systems, including at least 1–2 years specifically building
AI agents (tool-using agents, multi-step reasoning, orchestration patterns, or RAG/KB integrations)
➢ Demonstrated experience designing and operating production REST APIs and backend services at scale
➢ Experience with containerised deployments (Docker) and cloud-hosted runtime environments (AWS preferred)
➢ Career Band: B3 — refer to the Agentic Platform Engineer Career Banding Framework for full progression details
F. Preferred Qualifications (Nice to Have)
➢ Familiarity with agent protocols / interoperability patterns (e.g., A2A-style messaging expectations) and tool
integration frameworks (e.g., MCP-style “toolkit” servers)
➢ Experience with containerized deployments and cloud-hosted runtime environments used for agent execution
➢ Experience designing multi-tenant SaaS backends and data isolation strategies
G. Tech Context You Should Expect
➢ Platform: a multi-tenant agent platform supporting simple and custom agents, API-driven lifecycle
management, and toolkit/integration servers
➢ Interfaces: RESTful Agent API, plus agent packaging workflows (upload/download) and agent
configuration/schema endpoints
➢ Deployment/runtime: local container workflows + cloud-hosted runtime patterns (as used by the platform)
➢ Quality: emphasis on API test coverage and agent evaluation strategy (e.g., unit tests + evaluation frameworks)
H. What Success Looks Like (First 90 Days)
➢ Deliver 1–2 meaningful backend/API features that improve agent lifecycle, reliability, or operability
➢ Ship at least one production-ready agent improvement (behavior quality + tooling robustness) with repeatable
evaluation
➢ Establish a lightweight but real agent evaluation/testing approach the team can reuse for future agents and
releases