AI Engineer (LLM+ Agentic AI) - Contractual - 6 months

Overview

About the Company

Ivy Mobility is committed to leveraging cutting-edge technologies such as computer
vision, machine learning, and artificial intelligence to solve complex problems and
deliver innovative solutions to our customers. As a Computer Vision Engineer at Ivy
Mobility, you will have the opportunity to work on challenging projects and collaborate
with a diverse team of talented professionals. Join us in shaping the future of computer
vision and making a meaningful impact in the world.

We are seeking a highly skilled AI Engineer with strong hands-on experience in Large Language Models (LLMs) and Agentic AI systems to join our team. The ideal candidate will have 2+ years of direct LLM experience, 1+ year building Agentic AI solutions, and a proven track record using open-source AI frameworks and deploying multi-agent architectures in production environments.

This role will collaborate closely with Product, Engineering, and Data Science teams to design, build, and optimize next-gen GenAI solutions for real-world business problems.

Key Responsibilities
Design, develop, and deploy LLM-powered applications, including fine-tuning, RAG pipelines, and prompt engineering.

Build and optimize Agentic AI systems, including multi-agent orchestration, tool integrations, and workflow automation.

Architect and implement multi-agent frameworks using open-source toolkits such as LangChain, LlamaIndex, Haystack, AutoGen, CrewAI, Semantic Kernel, or related alternatives.

Develop scalable backend services to operationalize AI models using APIs, microservices, and event-driven workflows.

Evaluate, integrate, and customize open-source LLMs (Llama, Mistral, DeepSeek, Phi, etc.) for domain-specific tasks.

Implement RAG architectures using vector databases (Pinecone, Milvus, Weaviate, Chroma, etc.).

Deploy and maintain models using containerized environments (Docker, Kubernetes) and CI/CD pipelines.

Conduct benchmarking, model evaluation, and performance tuning for latency, accuracy, and cost efficiency.

Work cross-functionally to understand business needs and translate them into scalable AI solutions.

Ensure security, governance, compliance, and responsible AI practices across deployments.

Required Skills & Experience
3–5 years of hands-on experience in AI/ML engineering or related fields.

2+ years** working directly with** LLM**(OpenAI, Anthropic, Meta, Mistral, or similar).

1+ year building Agentic AI systems with multi-agent orchestration.

Experience with open-source frameworks such as LangChain, LlamaIndex, HuggingFace Transformers, CrewAI, AutoGen, or equivalents.

Proven experience deploying multi-agent solutions in production.

Strong software engineering skills in Python (preferred), with experience in FastAPI/Flask for serving models.

Solid understanding of vector databases, embeddings, RAG, and prompt engineering best practices.

Experience working with cloud platforms (Azure, AWS, GCP) and MLOps stacks.

Proficiency with Docker, Kubernetes, GitHub Actions/GitLab CI, or other DevOps tooling.

Experience with monitoring and observability tools for AI workloads.

Good-to-Have Skills
Experience fine-tuning or training custom LLMs.

Familiarity with Retrieval-Augmented Generation optimizations (caching, routing, re-ranking).

Background in microservices, event-driven architectures, and performance engineering.

Knowledge of enterprise AI governance, data privacy, and compliance frameworks.

Exposure to Computer vision is a plus.

Understanding of multi-modal AI (vision + LLMs) is an advantage.