GEN AI Engineer
Role summary
We are seeking a skilled GenAI Engineer to design, develop, and implement cutting-edge Generative AI solutions. This role involves working with Large Language Models (LLMs) and GenAI frameworks like LangChain, focusing on agentic AI concepts, vector databases, and semantic search. You will integrate these capabilities into applications and workflows, ensuring scalability, reliability, and cost-efficiency. The position requires strong Python skills, cloud platform experience (Azure, AWS, GCP), and a solid understanding of AI/ML fundamentals including NLP and deep learning. You will collaborate with cross-functional teams, translate business needs into AI-driven solutions, and contribute to AI best practices.
Job Description
Must Have Technical/Functional Skills
Technical Skills
Strong experience with Python (mandatory); exposure to Java/TypeScript is a plus.
Hands-on experience with LLMs and GenAI frameworks (e.g., LangChain-style orchestration, agent frameworks).
Experience with Agentic AI concepts: planning, tool use, memory, multi-agent coordination.
Experience with vector databases and semantic search.
API integration and microservices architecture.
Cloud platforms (Azure / AWS / GCP).
AI/ML Knowledge
Understanding of NLP, deep learning, and transformer-based models.
Experience with model evaluation, hallucination mitigation, and prompt optimization.
Familiarity with Responsible AI, security, and data privacy principles.
Roles & Responsibilities
GenAI Development
Design and implement GenAI solutions using LLMs for text, code, and knowledge-based use cases.
Develop prompt engineering, prompt orchestration, and reusable prompt libraries.
Fine-tune and evaluate LLMs for enterprise-specific tasks.
Integrate GenAI capabilities into applications, APIs, and workflows.
Agentic AI & Autonomous Systems
Design and implement agentic architectures (planner, executor, evaluator, memory).
Build multi-agent systems with task decomposition, tool usage, and feedback loops.
Enable agents to interact with enterprise tools, APIs, databases, and knowledge stores.
Implement agent memory, reasoning chains, and self-reflection mechanisms.
Architecture & Engineering
Define end-to-end AI solution architecture (cloud, APIs, security, observability).
Implement Retrieval-Augmented Generation (RAG) with vector databases.
Ensure scalability, performance, reliability, and cost efficiency.
Apply Responsible AI, governance, and compliance standards.
Collaboration & Delivery
Work closely with product owners, domain experts, and engineering teams.
Translate business problems into AI-driven solutions.
Support SDLC phases including design, development, testing, deployment, and support.
Mentor junior engineers and contribute to AI best practices.
Salary Range: $100,000-$130,000 a year
