Senior Software Engineer

Network Solutions, a part of Newfold Digital, is seeking a Senior AI Back-End Engineer to contribute to the development of their AI platform. This role involves designing and scaling asynchronous REST/WebSocket APIs using Python 3.11+ and FastAPI, focusing on dependency injection, type hints, and clean architecture. You will implement multi-agent workflows with Semantic Kernel for routing traffic among specialized LLM agents and integrate LLM providers (OpenAI GPT-4.1/mini, Google Gemini 2.5 Flash) through a provider-agnostic layer for A/B and cost-aware routing. The position requires delivering Retrieval-Augmented Generation (RAG) with vector stores like Azure AI Search, pgvector, or Chroma, and exposing tool-using agents via OpenAI Assistants (Code-Interpreter) for data analysis and file manipulation. Responsibilities also include evolving schemas with SQLModel/SQLAlchemy 2 and Alembic, tuning Postgres for high-concurrency async access, and maintaining CI/CD pipelines (Bitbucket Jenkins) for linting, testing, packaging (Docker), and deployment. You will instrument services with structured JSON logs, OpenTelemetry traces, and cost/latency metrics, aiming for p95 latency below 100 ms. Championing AI-assisted development tools like GitHub Copilot and Cursor, and sharing problem-solving practices are key aspects of this role.

The ideal candidate will have 5+ years of experience building production APIs in Python, with at least 2 years using FastAPI or a similar async stack. Deep knowledge of async I/O, Pydantic v2, dependency injection, and observability is essential. Hands-on experience with Semantic Kernel or comparable agent frameworks, practical RAG implementations, and strong Postgres skills (including SQLModel/SQLAlchemy 2 and Alembic migrations) are required. Proven integration or side project experience with LLM APIs (OpenAI, Gemini) and structured output design is also necessary. Familiarity with dependency management via Poetry and virtual-env isolation, end-to-end CI/CD ownership, and excellent analytical and problem-solving abilities are expected. The role requires readiness for remote work with daily overlap between 09:00 - 13:00 EST.

Nice to have: Experience with event/message queues (RabbitMQ, Azure Service Bus, Kafka) and observability stacks (Grafana, Lang Fuse) for LLM cost governance.

Join us to build the agent-powered backbone of our AI platform—robust, model-agnostic, and ready for millions of users. Newfold Digital offers a thrilling and meaningful work environment with a focus on work-life balance, diversity and inclusion, comprehensive health benefits, punctuality bonuses, generous vacation policies, and ample opportunities for career growth and development.