Senior Backend Engineer Agentic AI
Location: Hartford, CT 3 Days Onsite
Employment Type: Contract
Experience: 4 7 Years
About the Role
We are looking for a Senior Backend Engineer who can design and build production systems that combine strong software engineering fundamentals with hands-on exposure to modern AI/ML tooling - specifically Agentic AI workflows and Model Context Protocol (MCP) servers.
You do not need to come from a pure AI/ML background. What matters is strong core engineering skills, sound architectural judgment, and the ability to pick up - or already understand - how to integrate AI agents into real-world production systems.
Must-Have Skills
Python - strong, production-grade proficiency; primary programming language.
Databases - solid relational/SQL fundamentals, including schema design, query optimization, and data modeling.
Cloud platform - strong hands-on experience with Google Cloud Platform (GCP) preferred; AWS is an acceptable alternative.
4+ years of professional software engineering experience.
Design & Architecture
Strong grounding in modular design - clear separation of concerns, well-bounded components/services, and low coupling/high cohesion.
Ability to design systems that scale horizontally - statelessness where appropriate, partitioning/sharding strategy, load distribution, and avoiding single points of contention.
Working fluency in core design patterns and principles, including SOLID, domain-driven boundaries, event-driven/async patterns, idempotency, caching strategies, and API versioning.
Ability to understand when to apply or avoid specific design patterns.
Comfortable reasoning about tradeoffs such as consistency vs. availability, latency vs. throughput, build vs. buy, and synchronous vs. asynchronous workflows.
API & Real-Time Integration Best Practices
Strong grasp of RESTful API design - resource modeling, versioning, pagination, idempotency for retries, and proper status codes/error contracts.
Practical experience with WebSocket-based real-time communication - connection lifecycle management, reconnection/backoff strategy, heartbeat/keep-alive handling, and graceful degradation when a socket drops.
Understands tradeoffs between REST, WebSockets, and event-driven/streaming integration patterns and can select the right approach for the use case.
Follows security best practices for integrations - authentication/authorization (OAuth2, token scoping), input validation, rate limiting, and safe handling of external payloads.
Designs integrations for observability and resilience - structured logging, timeouts, circuit breakers, and clear failure modes rather than silent drops.