Role: Python GenAI
Location: Holtsville, NY
Duration: Long Term Contract – C2C
Interview: Video
GenAI / AI Engineering (60%)
- Design and build agentic AI platforms, orchestrating multi-agent workflows using frameworks such as CrewAI, LangGraph, or LangChain.
- Implement and optimize Retrieval-Augmented Generation (RAG) pipelines, ensuring high-quality retrieval, embeddings, and context enrichment.
- Develop and integrate modular AI agents for reasoning, summarization, planning, and decision support.
- Continuously evaluate and fine-tune LLM outputs, applying guardrails, monitoring, and human-in-the-loop feedback.
- Stay current with GenAI research and frameworks, recommending adoption of new tools and methodologies.
Full-Stack Development & Cloud Engineering (40%)
- Build and maintain full-stack applications around GenAI services using modern frameworks (React, Node.js/Express, FastAPI, etc.).
- Design and deploy cloud-native services on Azure (preferred), AWS, or GCP, with experience in containerization (Docker) and orchestration (Kubernetes or ACA).
- Integrate GenAI services into enterprise workflows, ensuring scalability, performance, and security.
- Collaborate across teams to translate business workflows into end-to-end AI-powered solutions.
- Document and standardize best practices for both GenAI pipelines and cloud-based application development.
Key Requirements
- Good to have Devices domain experience
- Hands-on experience with Agentic AI frameworks (CrewAI, LangGraph, LangChain, or similar).
- Deep understanding of RAG pipelines — chunking, embeddings, vector databases (Qdrant, Pinecone), and retrieval optimization.
- Proficiency in Python and GenAI development stacks (async processing, FastAPI, OpenAI/Azure SDKs).
- Strong background in LLM orchestration and prompt engineering for reasoning, planning, and decision-making agents.
- Solid full-stack development skills, including React (or similar frontend framework) and Node.js/Express or Python backends.
- Practical cloud deployment expertise in Azure (preferred), AWS, or GCP, with Docker/Kubernetes.
- Experience designing scalable AI + app architectures, including agent workflows, context passing, memory management, and streaming responses.
- Strong system design and problem-solving mindset, capable of building modular, reusable solutions.
—
—
