Senior AI Engineer (Generative AI)

Job Description

Dice is the leading career destination for tech experts at every stage of their careers. Our client, RITWIK Infotech Inc, is seeking the following. Apply via Dice today!

**(Visa accepted: H1B, L2 EAD)**
**Key Responsibilities**
**Generative AI Application Development**

– Design, develop, and deploy production-grade Generative AI applications such as RAG systems, AI copilots, content intelligence tools, and workflow automation solutions.
– Build scalable GenAI pipelines capable of handling large-scale enterprise workloads.

**Agentic AI Systems**

– Architect and implement agentic workflows including tool/function calling, planning mechanisms, memory management, verification loops, and multi-agent orchestration.
– Develop reliable automation systems with built-in guardrails and failure-handling mechanisms.

**Architecture & Scalability**

– Design secure, scalable, and cost-efficient architectures for batch and real-time AI workloads.
– Optimize performance including latency reduction, throughput improvement, and resource efficiency.

**Model Integration & AI Tooling**

– Evaluate and integrate large language models (LLMs) from hosted and open-source providers.
– Implement embeddings, reranking models, prompt engineering frameworks, and multimodal AI solutions.

**Evaluation & Quality Assurance**

– Build evaluation frameworks to measure accuracy, relevancy, hallucination rates, and safety compliance.
– Implement offline and online testing strategies, including A/B experimentation.

**Data Retrieval Systems**

– Design efficient RAG pipelines and retrieval architectures.
– Develop indexing pipelines, optimize chunking strategies, and implement vector search and caching mechanisms.

**AI Operations (LLMOps / MLOps)**

– Implement CI/CD pipelines for AI systems.
– Manage model versioning, prompt configuration management, automated testing, monitoring, and rollback strategies.

**Security & Governance**

– Ensure compliance with enterprise standards including data privacy, PII protection, audit logging, and access controls.
– Implement content filtering and governance frameworks aligned with regulatory requirements.

**Technical Leadership**

– Mentor junior engineers through code reviews, architecture guidance, and best practices.
– Define standards and frameworks for scalable AI engineering practices.

**Cross-Functional Collaboration**

– Partner with Product, Data, Platform, and Design teams to define solution architecture, delivery milestones, and success metrics.

**Required Qualifications**

– 6+ years of software engineering experience
– 3+ years of experience building ML/AI systems
– Hands-on experience developing production-grade Generative AI applications
– Proven expertise building agentic AI systems in production environments
– Strong programming skills in Python (preferred), TypeScript, Java, or Go
– Experience with:

– LLM integration and prompt engineering
– RAG pipelines and vector databases
– embeddings and retrieval optimization
– distributed systems (REST APIs, async processing, queues)
– cloud platforms (AWS / Google Cloud Platform / Azure)
– containerization (Docker, Kubernetes)

– Experience implementing monitoring, evaluation metrics, safety guardrails, and cost optimization for AI systems
– Ability to work independently and lead complex AI initiatives

**Preferred Qualifications**

– Experience with fine-tuning models (LoRA, PEFT)
– Experience building multi-modal AI systems
– Familiarity with GenAI orchestration frameworks and observability tools
– Knowledge of security and privacy standards (SOC2, HIPAA, PII protection)
– Experience defining technical roadmaps and enterprise AI architecture