AI Integration Engineer

Role: AI Integration Engineer

Long Term Project

Role Overview:

We are seeking an AI Integration Engineer to bridge the gap between foundation models and production enterprise applications. In this role, you will design, build, and maintain high-performance integration services and orchestrators that embed generative AI capabilities and autonomous workflows directly into core business systems. You will focus primarily on backend service implementation in Go, model API integrations (specifically leveraging Anthropic's Claude SDK), and designing resilient agentic architectures.

Key Responsibilities:

 Backend & Systems Integration: Architect and build concurrent, low-latency microservices and middleware in Go (Golang) to interface with foundation model APIs, context retrieval systems, and internal services.

 Agentic Orchestration: Design and implement autonomous and semi-autonomous multi-step agentic systems, including tool use/function calling, task routing, evaluation loops, and state management.

 Model Integration & Claude SDK: Leverage the Anthropic Claude SDK (and related model APIs) to integrate advanced reasoning, multimodal features, structured JSON outputs, and large-context document processing.

 Prompt Engineering & Optimization: Apply systematic prompt engineering techniques (chain-of-thought, few-shot prompting, system prompts, dynamic context windows) to maximize output reliability, reduce hallucinations, and control token usage.

 Codebase & Version Control: Maintain high code quality, test coverage, and documentation within team repositories using Git across GitLab or GitHub.

Required Qualifications:

 Proficiency in Go (Golang): Strong experience writing idiomatic, concurrent, and high-performance backend microservices (goroutines, channels, REST/gRPC interfaces).

 AI Model Integration & SDKs: Hands-on experience integrating with commercial LLM APIs, with direct experience using the Claude SDK / Anthropic API for structured data extraction and tool calling.

 Prompt Engineering: Demonstrated expertise in designing, testing, and optimizing system prompts, dynamic templates, and evaluation strategies for reliable model responses.

 Version Control & Collaboration: Proficient with Git and platform workflows in GitLab or GitHub(PRs/MRs, branch management, code review hygiene).

Preferred Qualifications:

 Experience building or integrating standard tool-use protocols (such as Model Context Protocol / MCP or custom tool schemas).

 Familiarity with vector databases, semantic search, and hybrid Retrieval-Augmented Generation (RAG) pipelines.

 Understanding of LLM evaluation frameworks, token optimization strategies, and latency/cost mitigation patterns (caching, streaming, batching).