Location: Remote
Must Have: RAG
Role Overview
We are seeking a highly skilled and strategic Senior AI Engineer / AI Product Solutions Architect to lead the design, development, and deployment of enterprise-grade Generative AI applications and automation workflows. In this role, you will bridge the gap between cutting-edge AI research and scalable production engineering. You will collaborate directly with cross-functional leadership, product managers, and engineering teams to transform complex operational data and legacy workflows into intelligent, automated, and secure enterprise solutions.
The ideal candidate has a proven track record of orchestrating multi-agent LLM architectures, building robust Retrieval-Augmented Generation (RAG) pipelines, and deploying highly available, serverless cloud architectures.
Key Responsibilities
AI Strategy & Orchestration: Spearhead the design and prioritization of enterprise-scale AI use cases, workflow automations, and intelligent agent orchestration utilizing frameworks like LangChain, LangGraph, and CrewAI.
System Architecture: Design, build, and deploy high-performance, horizontally scalable document pipelines and conversational AI platforms (handling 1000+ transcripts/documents per minute) with strict p95 latency targets and 99.9% availability.
Advanced NLP & Prompt Engineering: Implement sophisticated Chain-of-Thought reasoning flows, custom prompt templates, function calling mechanisms, and structured output parsing using state-of-the-art models (e.g., GPT-4o, Gemini) to extract and categorize complex data with high precision.
Vector Search & Retrieval: Architect robust RAG pipelines and semantic search systems utilizing high-dimensional embeddings (e.g., Ada-002) and vector databases like Milvus or Pinecone to intelligently route queries and parse multi-format data.
Full-Stack & Cloud Integration: Develop robust backend REST APIs (FastAPI, Java/Spring Boot) and highly responsive frontend interfaces (React, VueJS) integrated seamlessly with cloud services across AWS and Azure.
Data & Pipeline Engineering: Optimize transactional APIs and distributed workflow engines (using SQS/Kinesis/Kafka) ensuring strict data idempotency, atomicity, and handling backpressure spikes smoothly.
Required Technical Skills
Generative AI & LLMs: LangChain, LangGraph, CrewAI, Model Context Protocol (MCP), ReAct, Fine-Tuning (LoRA, RLHF), OpenAI GPT-4o, Google Gemini, Mistral 7B, Hugging Face.
Programming Languages: Expert-level Python; strong proficiency in Kotlin, Java, and TypeScript/JavaScript.
Data & Vector Databases: Milvus, Pinecone, Redis (for persistent chat memory), MongoDB, DynamoDB, and PostgreSQL.
Cloud & DevOps: AWS (Lambda, SQS, Kinesis, ECS, S3, CloudWatch, SageMaker) and Azure (Azure OpenAI, Azure Document Intelligence).
Frontend Frameworks: ReactJS, VueJS, or AngularJS.
Document Intelligence & OCR: PyPDF2, Pytesseract, and intelligent token-aware chunking strategies.
Qualifications
Education: Master’s degree in Computer Science or a deeply technical related field (GPA 4.0 preferred) with advanced coursework in Statistical Machine Learning, NLP, and Distributed DBMS.
Experience: 4+ years of professional software engineering experience, with at least 2 years dedicated heavily to deploying production-level Generative AI and LLM orchestration applications.
Soft Skills: Outstanding cross-functional collaboration skills; ability to communicate complex technical AI concepts to both founding teams and engineering peers.