Full Stack AI Engineer

About the Role

Optimize Solutions is hiring a Full Stack AI Engineer to design, develop, and deploy AI-powered products end-to-end. In this role, you’ll combine your expertise in Node.js, Python, and modern web frameworks with advanced AI/LLM integration to create scalable, intelligent systems. You’ll work across the full stack — from backend APIs and AI pipelines to frontend interfaces and deployment — collaborating with product, design, and data teams to deliver safe, efficient, and user-centered AI applications. This is an exciting opportunity to shape next-generation AI experiences while applying your engineering and problem-solving skills in a production environment.

Key Responsibilities

• Design, test, and refine prompts (zero-shot, few-shot, chain-of-thought, ReAct) across models like GPT-4/4o, Claude, Mistral, and Llama.
• Implement function calling, structured outputs, and guardrails for safety, reliability, and cost efficiency.
• Build production-grade RAG pipelines, handling chunking, retrieval orchestration, and embedding optimization.
• Analyze LLM outputs for hallucinations, bias, factual accuracy, and alignment with business needs.
• Develop polyglot services using Node.js (Fastify) and Python (FastAPI).
• Implement OAuth2/JWT, rate limiting, retries/backoff, and real-time streaming (SSE/WebSockets).
• Integrate vector databases (Pinecone, Weaviate, Qdrant) and relational/non-relational databases (PostgreSQL, MongoDB).
• Use CI/CD, Docker, and cloud deployment tools (Azure or AWS) for production releases.
• Instrument applications with logging, telemetry, and cost/latency monitoring.
• Build user interfaces using Next.js (TypeScript, App Router) and React Server Components.
• Deliver chat UIs, admin dashboards, evaluation tools, and prompt versioning systems with real-time updates.
• Maintain a version-controlled prompt library with documentation and test coverage.
• Run A/B experiments, structured evaluations, and regression testing for prompt performance.
• Apply Responsible AI practices — mitigate misuse, prompt injection, and privacy risks.
• Stay up-to-date on emerging AI/LLM trends and frameworks, sharing knowledge with the team.

What We’re Looking For

• Bachelor’s degree in Computer Science, Software Engineering, AI/ML, or a related field.
• 3+ years of professional full-stack development (production APIs & web apps).
• 2+ years of hands-on AI/LLM experience (prompt engineering, RAG, LLM APIs).
• Languages & Frameworks: Advanced JavaScript/TypeScript, Node.js (Fastify/Express), Python (FastAPI)
• APIs: REST, GraphQL, OAuth2/JWT, rate limiting, retries/backoff, and streaming via SSE/WebSockets.
• Databases: PostgreSQL, MongoDB; ORM experience with Prisma and schema migrations.
• AI/LLM Tools: OpenAI, Anthropic, Mistral, Llama; LangChain or LlamaIndex, PromptLayer, RAG design.
• Vector Databases: Pinecone, Weaviate, Qdrant; embeddings, hybrid retrieval, and evaluation pipelines.
• DevOps: Docker, Kubernetes, CI/CD, observability (metrics, tracing, cost telemetry).
• Security: Data privacy compliance, prompt-injection defense, content safety measures.
• Strong analytical and problem-solving mindset.
• Excellent collaboration and communication in a remote setting.
• Passion for innovation, continuous learning, and responsible AI practices.