AI Engineer

• Build, integrate, and optimize AI Assistants and agent-based solutions capable of retrieving information, executing workflows, and supporting business processes through natural language interactions.
• Develop and maintain integrations with enterprise data sources, APIs, knowledge bases, document repositories, and business applications to enable accurate and context-aware AI experiences.
• Implement prompt engineering, grounding, retrieval, memory management, and agent orchestration techniques to improve response quality, reliability, and user experience.
• Develop document ingestion, metadata extraction, chunking, indexing, and knowledge management pipelines to support enterprise search and AI Assistant capabilities.
• Evaluate, test, and optimize AI solutions using techniques such as prompt tuning, model selection, caching, reranking, and retrieval optimization to improve accuracy, latency, and cost efficiency.
• Collaborate with product, engineering, and domain teams to define requirements, translate business needs into AI capabilities, and deliver production-ready solutions.
• Implement observability, monitoring, evaluation, and feedback mechanisms to measure AI Assistant performance, identify issues, and drive continuous improvement.
• Support deployment, productionization, and operational readiness activities, including security, entitlements, access controls, auditability, and governance requirements.
• Stay current with advancements in LLMs, agent frameworks, RAG architectures, vector databases, knowledge graphs, and AI platform technologies, and contribute to the adoption of relevant capabilities.

Required Skills:

• Experience with Agentic AI frameworks such as LangGraph, Semantic Kernel, CrewAI, AutoGen, or similar orchestration platforms.
• Familiarity with Retrieval-Augmented Generation (RAG) architectures, vector databases (Milvus, Pinecone) and enterprise knowledge base implementations.
• Experience building and deploying AI Assistants, Copilots, or conversational AI solutions for business or operational use cases.
• Exposure to agent orchestration, tool calling, workflow automation, and multi-agent systems.
• Deep expertise in Python especially with PyTorch/TensorFlow (model training, fine-tuning for vision, text, and audio; Supervised, Unsupervised, Reinforcement learning experience is a plus).
• Knowledge of Machine Learning techniques: anomaly detection, predictive analytics

Nice to Have Skills:

• Knowledge of document ingestion, OCR, metadata extraction, and document processing frameworks such as Textract, Docling, or equivalent technologies.
• Understanding of LLM evaluation, observability, prompt engineering, and responsible AI practices.
• Familiarity with Graph databases, Knowledge Graphs, and Ontology-based retrieval and reasoning.
• Experience integrating AI solutions with enterprise platforms through REST APIs, FastAPI, microservices, and event-driven architectures.
• Exposure to cloud-based AI services such as Azure OpenAI, AWS Bedrock, Amazon Textract, Azure AI Foundry, or similar platforms.
  • Knowledge of security concepts including OAuth, OIDC, RBAC, entitlements, auditability, and enterprise AI governance.