AI Engineer (Remote) P.HD Candidates Only

Gen AI Engineer – AI/LLM Backend Focus

(Contract to Hire, Remote – U.S. Eastern

Time Zone)

Location: Remote (U.S. Only, Eastern Time working hours)

Role Overview

We are seeking a Gen AI Engineer with deep expertise in large language model (LLM) architectures to join our tightknit team. In this role, you will design and implement cutting-edge AI/LLM backend systems that power intelligent applications—everything from chatbots to semiautonomous agents. You’ll architect robust backends: orchestrating agentic workflows, retrievalaugmented generation (RAG) pipelines, and highperformance knowledge bases. 

This is a fully remote position (U.S. only) with flexible hours on Eastern Time. We welcome both parttime and fulltime contractors for this role. You’ll collaborate virtually to build AIdriven solutions that innovate and scale.

Key Requirements

• LLM Framework Expertise: Deep experience with frameworks such as LangChain, LangGraph, Crew AI, or equivalent for building conversational and agentdriven applications.

• Agentic Workflows: Strong understanding of agent types and paradigms—ReAct (reasonact), planning agents, reflective agents—and handson experience implementing multistep AI workflows.

• RetrievalAugmented Generation (RAG): Advanced knowledge of RAG techniques, including graph RAG, hybrid RAG, and agentic RAG implementations to augment LLMs with external knowledge.

• Knowledge Bases & Vector Databases: Experience building and maintaining scalable vectorbased knowledge bases (e.g., Pinecone, Weaviate). Proficiency optimizing vector search with approximate nearest neighbor (ANN) algorithms (HNSW, IVF, PQ), reranking techniques, maxinnerproduct search, cosine similarity, and libraries like

Faiss, Annoy, or similar.

• Python & Pydantic: Expert in Python, with strong use of Pydantic for data validation and modeling in AI pipelines.

• Model Finetuning & Evaluation: Handson experience finetuning LLMs and using evaluation frameworks such as LangSmith to measure and improve model performance.

• MCP Protocol: Understanding of the Model Context Protocol (MCP) and how to integrate MCP servers and clients for dynamic context management.

• AWS Bedrock: Familiarity with AWS Bedrock services for deploying and scaling AI models, or demonstrated ability to learn quickly.

• VoiceEnabled AI: Experience integrating voiceenabled AI technologies, such as OpenAI’s realtime Voice API.

• Model Providers & Private LLMs: Proven experience working with major API model providers (OpenAI, Anthropic Claude, Google Gemini) as well as opensource LLMs (e.g., Meta’s Llama), including hosting private LLM instances and integrating diverse provider APIs.

• Front-end experience with React; backend experience with js and TypeScript.

Preferred Qualifications

• Cloud Deployment: Proven record deploying LLM applications on cloud platforms (AWS preferred), including CI/CD, containerization (Docker), and security best practices for AI services.

• Prompt Engineering: Mastery of prompt design and engineering techniques, with an emphasis on systematic evaluation and optimization.

• AINative Architecture Design: Ability to architect modular, scalable AIfirst systems, leveraging serverless functions or pipeline patterns optimized for AI/ML workloads.

Application Domains

Work on diverse AIdriven projects, such as:

• LLMPowered Chatbots: Scalable conversational agents for customer support, knowledge retrieval, or virtual assistants.

• Workflow Automation: Intelligent automation tools that orchestrate business processes and decision logic with minimal human supervision.

• SemiAutonomous Agents: Systems of collaborative agents employing planning and reflection to achieve complex tasks.