AI Integration Engineer

Job Description

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).