Overview
Flyte Solutions Ltd. is looking for a Lead Generative AI Engineer to drive the architecture, engineering, and production deployment of enterprise-scale Generative AI solutions. This is a senior technical leadership and hands-on engineering role for someone with deep expertise in LLMs, RAG, Agentic AI, LLMOps, AI infrastructure, and distributed systems. The successful candidate will help shape enterprise AI architecture while leading the development of secure, scalable, reliable, and cost-efficient AI platforms and applications.
Key Responsibilities
- •Define the architecture, engineering standards, and technical direction for enterprise GenAI platforms and applications.
- •Architect scalable, secure, reliable, and cost-efficient AI platforms, infrastructure, and reusable AI services.
- •Design and productionize advanced RAG pipelines, including ingestion, chunking, embeddings, vector retrieval, reranking, context management, and evaluation.
- •Establish best practices for LLMOps, prompt management, agent orchestration, AI observability, model evaluation, guardrails, and AI governance.
- •Lead the development of enterprise AI copilots, conversational BI solutions, AI-powered customer service assistants, recommendation engines, knowledge retrieval systems, and autonomous workflow agents.
- •Design sophisticated multi-agent and tool-calling workflows integrated with enterprise APIs, databases, applications, and external services.
- •Drive GenAI solutions from architecture and proof-of-concept through production deployment, scaling, monitoring, and optimization.
- •Optimize latency, throughput, GPU utilization, inference cost, scalability, reliability, and model performance.
- •Implement strategies for hallucination mitigation, AI evaluation, security, privacy, Responsible AI, and enterprise compliance.
- •Evaluate emerging LLMs, AI frameworks, inference technologies, vector databases, and orchestration platforms to guide the enterprise AI technology roadmap.
- •Mentor AI/ML and GenAI engineers and provide technical leadership across multiple AI initiatives.
- •Partner with business, product, and technology stakeholders to convert high-impact business opportunities into scalable AI solutions.
- •Contribute to enterprise AI strategy, architecture, governance, and technology roadmap.
Required Experience
- •7+ years of professional experience across AI/ML engineering, software engineering, distributed systems, enterprise platforms, or related areas.
- •Proven experience architecting, developing, and deploying production-grade AI/GenAI systems at scale.
- •Strong hands-on experience taking AI solutions from concept and architecture to production deployment and optimization.
- •Previous experience leading technical teams, AI engineering squads, or providing architecture and engineering leadership.
Technical Expertise
- •LLM application development, prompt engineering, RAG architectures, semantic search, embeddings, vector retrieval, AI agents, tool/function calling, multi-agent orchestration, context and memory management, model evaluation, guardrails, and hallucination mitigation.
- •Strong proficiency in Python, backend/API engineering, FastAPI or equivalent frameworks, distributed systems, scalable architectures, and enterprise integrations.
- •Hands-on experience with technologies such as LangChain, LlamaIndex, MLflow, vector databases, AI evaluation/observability tools, and agent orchestration frameworks.
- •Experience with GPU-based inference, open-source LLM deployment, model serving, LoRA/PEFT fine-tuning, distributed AI workloads, Docker, Kubernetes, CI/CD, DevOps, and cloud-native AI architectures.
- •Hands-on familiarity with one or more major cloud ecosystems: AWS, Microsoft Azure, or Google Cloud Platform.
Leadership and Professional Capabilities
- •Strong architecture and technical decision-making skills.
- •Ability to mentor engineers and lead multiple AI initiatives with minimal supervision.
- •Experience with AI governance and Responsible AI.
- •Excellent problem-solving capability.
- •Strong stakeholder communication and presentation skills.
- •Comfortable collaborating with engineering, product, business, security, and leadership teams.
Academic Qualification
Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, Applied Statistics, Information Technology, Business/Analytics, or another relevant discipline.
Preferred Qualifications
- •Experience with enterprise-scale RAG and Agentic AI systems.
- •Open-source LLM deployment and optimization.
- •GPU and inference infrastructure experience.
- •LLMOps or enterprise AI platform architecture.
- •AI governance and compliance experience.
- •High-volume or mission-critical application experience.
- •Relevant AI or cloud certifications.
- •Open-source contributions, patents, research publications, or conference presentations.
How to Apply
Send your updated CV to career(@)flytesolutions.com with the subject line: Lead AI Engineer_7Years
Please include your updated resume, current salary, expected salary, notice period, and optionally your GitHub and LinkedIn profiles.
Location and Details
- •Position: Lead Generative AI Engineer
- •Employment Type: Full-Time
- •Location: Bangladesh
- •Experience: 7+ Years
- •Company: Flyte Solutions Ltd., Banani, Dhaka 1213, Bangladesh