Staff Software Engineer Python & AI Agent Security Platform

Why Join Skyrelis?Build the world’s leading AI security & observability platform.Work on cutting-edge multi-cloud infrastructure and global PoP architecture.Own complex security + cloud problems end-to-end.Significant growth opportunity as one of the early engineers building the Skyrelis platform.About the roleSkyrelis is looking for a Member of Technical Staff (MTS) / Staff Software Backend/Platform Engineer contractor to lead the design and development of cloud-native, Python-first systems that power AI agents, LLM integrations, safety/guardrails, and secure traffic inspection across modern deployments. This is a backend/platform role focused on production systems, security, and reliability. You will work on architecture, core platform services, proxy/HTTP systems, data pipelines, and AI agent runtime controls—shipping production-grade software with high reliability and strong security posture.ResponsibilitiesLead system design and architecture for scalable backend/platform services supporting AI agents and LLM-driven workflows.Build and maintain Python services and libraries (APIs, pipelines, policy engines, telemetry, integrations).Develop secure, high-performance components involving:HTTP/HTTPS, TLS, certificates, and request/response processingForward/explicit proxies, service-to-service traffic interception, and policy enforcementDesign and implement guardrails/safety controls for AI agent workflows (prompt/response filtering, tool-use controls, policy checks, data loss prevention patterns).Build cloud-native deployments on AWS and/or GCP, including CI/CD, observability, and cost-aware scalability.Drive debugging and incident resolution: deep dives across app, network, and infra layers.Design data models and storage for operational analytics using OpenSearch/PostgreSQL and related systems.Collaborate with product, security, and infra teams to define roadmaps, technical direction, and best practices.Mentor engineers and raise engineering quality through reviews, design docs, and operational excellence.Required QualificationsBS/MS in Computer Science, Engineering, or equivalent practical experience.7+ years of hands-on software development experience with strong ownership of production systems.Strong background in design and architecture (distributed systems, APIs, reliability, scaling).Strong Python development experience; comfortable with additional languages (e.g., Go/Java/TypeScript/Rust).5+ years of working experience with FASTAPI or any other Python web framework.Working knowledge of AWS and/or GCP cloud deployments (networking, compute, IAM, security).Excellent debugging skills across application, network, and infrastructure layers.Solid understanding of HTTP/HTTPS protocols, TLS, certificates, and traffic flows.Knowledge/experience with proxies (forward/explicit/reverse), authentication patterns, and request/response transformations.Experience with databases and search/analytics systems: PostgreSQL, OpenSearch/Elasticsearch (indexing, mappings, query patterns).Preferred QualificationsKnowledge of AI / LLM / Agent Technology RequirementsHands-on experience building AI agents using common frameworks (e.g., LangChain/LangGraph, LlamaIndex, Semantic Kernel) and core patterns like tool/function calling, planning/execution, memory, RAG, and multi-agent workflows.Practical integration with LLM services/APIs (e.g., OpenAI/Azure OpenAI, Anthropic, Google Vertex/Gemini, AWS Bedrock) including streaming, structured outputs, routing/fallbacks.Experience implementing guardrails and safety controls (policy enforcement, prompt-injection defenses, PII/secrets detection, moderation, tool-use restrictions; tools like Prompt Guard, Guardrails AI, NeMo Guardrails, LLM Guard, etc.)Strong understanding of RAG and retrieval systems, including embeddings, chunking/ranking, and using vector search (OpenSearch vector, pgvector, Pinecone/Weaviate/Milvus/FAISS).Familiarity with evaluation and observability for LLM/agent systems: quality/safety metrics, cost/token tracking, OpenTelemetry tracing/logging.Experience building security products (DLP, policy enforcement, identity integration, audit logging).Experience with service mesh / sidecars (Istio/Envoy), certificate automation, or SDS/mTLS concepts.Experience with Kubernetes (EKS/GKE), Terraform/CloudFormation, and production operations.Experience with OpenSearch (data streams, index templates, ISM/ILM, dashboards) and performance tuning.Tech StackLanguages: Python (primary), plus Go/Java/TypeScriptCloud: AWS/GCP, VPC networking, IAM, load balancers, CDNData: PostgreSQL, OpenSearch, Redis; optional vector DBsAI: LangChain/LangGraph, LlamaIndex; OpenAI/Bedrock/Vertex/Gemini/AnthropicObservability: OpenTelemetry, logs/metrics/traces, dashboards/alertingSecurity/Networking: HTTP/HTTPS, TLS, proxies, authN/authZ, guardrailsSoft SkillsStrong ownership and execution abilities.Excellent communication and documentation skills.Ability to operate independently in a fast-moving startup environment.Comfortable collaborating with engineering, security, and customer teams.We’re grateful to everyone who takes the time to apply. While we’re unable to respond to every applicant, we’ll be in touch directly with those whose experience aligns closely with the role.

Apply Now