About the Role :

- We are seeking an experienced AI Integration Engineer to build and deploy AI-powered capabilities into production applications.

- The ideal candidate will have strong experience integrating Large Language Model (LLM) APIs, designing Retrieval-Augmented Generation (RAG) pipelines, and building scalable AI workflows.

- This role requires collaboration with cross-functional engineering teams to deliver secure, reliable, and production-ready AI solutions that enhance user experiences.

Job Responsibilities :

- Integrate LLM APIs such as OpenAI GPT-4o, Anthropic Claude, AWS Bedrock, and Google Gemini into backend services and user-facing applications.

- Design and implement RAG pipelines, including document ingestion, chunking strategies, vector database integration, and retrieval optimization.

- Build and maintain agentic AI workflows using frameworks such as LangChain, LlamaIndex, AgentCore, CrewAI, or custom orchestration patterns.

- Develop and manage prompt engineering strategies, prompt versioning, and prompt evaluation frameworks.

- Implement AI guardrails, including output validation, content filtering, fallback mechanisms, and safety controls.

- Monitor AI application performance, including latency, token usage, cost optimization, and model accuracy.

- Collaborate with frontend and backend engineering teams to integrate AI capabilities into product workflows.

- Manage the AI integration lifecycle from design and development through CI/CD, deployment, monitoring, and production support.

Required Skills :

- 3+ years of Backend or Full Stack development experience with strong API design and integration skills.

- Proven experience integrating LLM APIs (OpenAI, Anthropic, AWS Bedrock, Google Gemini, or similar) into production applications.

- Strong programming skills in Python and/or TypeScript/Node.js.

- Hands-on experience designing and implementing RAG architectures using vector databases such as Pinecone, Weaviate, pgvector, or similar.

- Strong understanding of prompt engineering, including system prompts, few-shot prompting, structured outputs, and prompt optimization.

- Experience with API security, authentication, rate limiting, and LLM cost management.

- Experience working with AWS or another major cloud platform.

- Strong troubleshooting, debugging, and problem-solving skills.

Preferred Skills :

- Experience with AI agent frameworks such as LangChain, LlamaIndex, AgentCore, CrewAI, AutoGen, or similar.

- Familiarity with multimodal AI capabilities, including vision, audio, function calling, and tool integration.

- Understanding of AI model fine-tuning concepts and workflows.

- Experience using AI-assisted development tools to improve engineering productivity.

- Exposure to CI/CD pipelines, containerization, and cloud-native application deployment.

Soft Skills :

- Excellent communication and interpersonal skills.

- Strong collaboration and stakeholder management abilities.

- Self-driven with a strong sense of ownership, accountability, and continuous learning.