Senior AI Integration Engineer
Posted 1hrs ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Senior Integration Engineer responsible for building secure APIs and data delivery services for AI applications. Requires extensive experience in backend engineering and high-performance systems.
Responsibilities:
- Build high-performance, secure, and production-grade API layers
- Develop custom Model Context Protocol (MCP) servers
- Implement real-time data delivery services optimized for human applications and autonomous AI agents
- Operate at high throughput — handling thousands of requests per second
- Build integration layers relied on by AI agents
Requirements:
- **Must-Have**
- Overall Experience: 8+ years in Backend Software Engineering, Distributed Systems Architecture, or Enterprise Platform Engineering
- Resiliency Engineering: 4+ years architecting mission-critical systems requiring "four-nines" (99.99%) availability, rigorous traffic shaping, and self-healing systems
- AI & Agentic Systems: 2+ years building production-grade integration layers, semantic context gateways, or RAG endpoints consumed by LLMs and autonomous AI agents
- Proficiency in Advanced API Design & Context Optimization
- Production-level proficiency in one or more of: C# (.NET Core), Java, Python, or Node.js/TypeScript
- Proficiency in Enterprise Scalability & Traffic Management
- Proficiency in Lock & Contention Mitigation (API & Database Tier)
- Proficiency in Hardened Security, Governance & AI Isolation
- **Preferred Experience**
- GraphQL and dynamic JSON/gRPC filtering layers (zero-waste data fetching)
- Custom MCP server development for LLM context exposure
- Heterogeneous schema merging for LLM tool-calling (e.g., relational DBs, analytics platforms like Pendo/Hotjar, observability tools)
- Semantic token-aware API pagination and streaming
- Context-aware gateways for conditional object graph hydration based on agent intent
- Edge performance: CloudFront Functions, Lambda@Edge, HTTP/3, WebSockets
- PostgreSQL and OpenSearch/Elasticsearch access layers with sub-millisecond caching
- Reactive streams and rate-limiting for Amazon MSK (Kafka), SQS, and HTTP endpoints
- Circuit Breakers, Bulkheads, and Retry-with-Exponential-Backoff (Polly, Resilience4j, or equivalent)
- Amazon MemoryDB / Redis OSS / Valkey for rate limiters, session caches, and semantic query caching
- Optimistic Concurrency Control (OCC) via eTags/versions; Pessimistic Locking only where strictly necessary
- CQRS separating high-volume writes from intensive read queries in PostgreSQL
- Asynchronous write delegation for high-contention API writes to Kafka/MSK
- Zero Trust security: OAuth2, OIDC, mTLS, and AWS Lake Formation
- Security proxy layers over Amazon Bedrock (prompt injection filtering, PII redaction, API token quota enforcement)
- End-to-end API runtime tracing with OpenTelemetry (oTel) and Datadog
Benefits:
- Remote work
- 13 floating holiday
- 15 vacation days per year completed
- Good working environment



















