Job Summary:
Scalence L.L.C. is seeking a Gen AI Tech Lead to oversee the design, development, and deployment of advanced NLP and cognitive search solutions. The role involves leading development efforts in AI-driven intelligent systems and collaborating with multidisciplinary teams to implement scalable solutions using various AI methodologies.
Responsibilities:
• Design scalable, maintainable AI solutions that integrate Langchain, LangGraph, and RAG methodologies to enhance knowledge discovery and conversational AI capabilities.
• Lead development efforts using Python to prototype and productionize AI agents and workflows.
• Collaborate with data engineering and DevOps teams to implement data pipelines and model deployment strategies.
• Develop and optimize RAG systems combining vector search, knowledge graphs, and LLMs to provide contextual and accurate responses.
• Architect agentic AI systems that perform autonomous tasks by chaining actions, managing states, and integrating external APIs.
• Provide technical leadership and architecture guidance for AI and NLP projects.
• Evaluate emerging AI technologies and frameworks to continuously improve solution design.
• Create comprehensive technical documentation and architecture diagrams to facilitate knowledge transfer.
• Ensure solutions meet security, compliance, and performance standards.
Qualifications:
Required:
• Strong proficiency in Python, with experience in backend or AI service development.
• Hands-on experience with Langchain and/or LangGraph frameworks.
• Deep understanding of Retrieval-Augmented Generation (RAG) systems and techniques.
• Experience designing and implementing agentic AI architectures, autonomous workflows, or multi-agent systems.
• Familiarity with knowledge graphs, vector search engines (e.g., FAISS, Pinecone, Weaviate), and LLM integration.
• Solid understanding of NLP concepts, transformer models, and prompt engineering.
• Ability to translate complex business requirements into scalable AI solutions.
• Experience with cloud platforms (AWS, GCP, Azure) and container orchestration (Docker, Kubernetes).
• Strong communication skills and ability to collaborate across multidisciplinary teams.
• 5+ years of professional software engineering experience, with at least 2 years building LLM-powered or agentic applications in production.
• Strong Python skills async/await, type hints, modern tooling (uv, ruff, pyright).
• Hands-on experience with LangChain, LangGraph, or equivalent agent frameworks.
• Experience designing and operating microservices with async Python web frameworks (FastAPI, Starlette).
• Solid understanding of relational databases PostgreSQL, schema design, migrations (Alembic/similar), query optimization, and async ORMs (SQLAlchemy 2.0).
• Experience with message-driven architectures RabbitMQ, Kafka, or similar broker-based async processing.
• Familiarity with vector databases and embeddings building RAG pipelines, semantic search, chunking strategies.
• Working knowledge of React and TypeScript able to understand and modify frontend features, not just consume APIs.
• Experience with Docker, Kubernetes, and CI/CD in cloud environments (Azure preferred).
• Experience with LLM provider APIs (OpenAI API or compatible providers) model configuration, streaming responses, token management, and structured output.
• Strong understanding of prompt engineering system prompts, multi-agent prompt architectures.
Company:
In today’s dynamic and competitive market, success hinges on mastering three key areas: Data Intelligence, Business Resilience, and Digital Experience. Founded in , the company is headquartered in Morristown, USA, with a team of 501-1000 employees. The company is currently Late Stage.