Job Description
Role: Lead Agentic AI engineer
Location: Dallas, TX, Atlanta, GA, Boston, MA, Chicago, IL (Hybrid)
Duration: W2 Contract (Independent candidates on W2)
This position will design and build intelligent AI agent systems, LLM-based applications, and autonomous workflow solutions within the context of our enterprise applications. We are looking for a candidate to provide expertise in Large Language Models, multi-agent architectures, RAG systems, Python development, cloud AI services, and enterprise AI integration. This individual will have broad experience in developing and deploying agentic AI solutions that can autonomously perform complex business tasks.
Experience & Skills
- 4-6 years’ hands-on experience working as Sr AI/ML Developer with at least three complete agentic AI system implementations
- 4-6 years’ hands-on experience with cloud AI services (Azure OpenAI, AWS Bedrock, Google Vertex AI)
- 4-6 years hands-on experience with Python AI/ML frameworks (LangChain, LlamaIndex, Transformers, PyTorch)
- 4-6 years’ hands-on experience integrating LLMs with external systems and enterprise applications
- Experience working with vector databases, knowledge graphs, and RAG pipeline development
- Advising on best practices for AI agent development and enterprise AI integration processes
- Experience in deploying AI models and agents in multiple environments (dev, staging, production)
- Experience managing stakeholder communication regarding AI capabilities, limitations, and project timelines, including managing expectations, foreseeing AI-related risks and reporting them
Technical Skills & Competencies
- Python, FastAPI, Flask
- LangChain, LlamaIndex, Transformers library
- OpenAI API, Azure OpenAI, Anthropic Claude
- Vector databases (Pinecone, Weaviate, ChromaDB)
- Git, Docker, Kubernetes
- JavaScript/TypeScript for AI integration
- Postman for API testing
- SQL/NoSQL databases for AI data management
- Sound knowledge in cloud AI services and MLOps
- AI model performance monitoring and optimization
- Prompt engineering and AI safety practices
Responsibilities
- Proficient in developing, deploying, and orchestrating multi-agent AI systems
- Demonstrated proficiency in LLM fine-tuning, prompt engineering, and model optimization
- Demonstrated proficiency in designing and implementing RAG (Retrieval-Augmented Generation) systems
- Demonstrated proficiency in understanding and implementing autonomous business workflows and AI-driven processes
- Demonstrated proficiency in using AI frameworks like LangChain, LlamaIndex, and Hugging Face ecosystem
- Demonstrated proficiency with Python development and AI/ML libraries
- Demonstrated proficiency in JavaScript/TypeScript for AI frontend integration
- Ability to perform AI model performance tuning and optimization in production environments
- Familiarity with MLOps tools and practices
- Experience in building conversational AI interfaces, chatbots, and AI-powered applications
- Experience with API development for AI services and webhook management
- Experience with cloud AI platforms (Azure OpenAI, AWS Bedrock, Google Cloud AI)
- Experience in AI agent orchestration, planning algorithms, and decision-making frameworks
- Creating and maintaining vector databases and knowledge management systems
- Experience producing AI system architecture and technical design documentation
- Must have college degree in Computer Science, AI/ML, or equivalent experience
Regards,
Praveen