AI Engineer

About the role

We're looking for an AI Engineer with 3–5 years of experience to design and deliver production-grade AI solutions for our clients. This is not a research role — you'll be building real systems: multi-agent architectures, retrieval-augmented generation pipelines, fine-tuned models, and AI-powered applications that solve concrete business problems.

You'll own the full lifecycle of AI solution development — from translating a client's use case into a technical architecture, through implementation and deployment, to iteration and optimization in production. You'll be the technical lead on AI engagements, working closely with data engineers, clients, and cross-functional teams to deliver solutions that are reliable, explainable, and built to scale.

What you'll do

• Architect and build end-to-end agentic AI systems using frameworks such as LangChain, LangGraph, LlamaIndex, and AutoGen — designing multi-agent workflows that reason, plan, and act across tools and data sources
• Design and implement advanced RAG pipelines including hybrid search, re-ranking, contextual chunking strategies, and retrieval evaluation — going beyond naive RAG to production-quality knowledge retrieval systems
• Fine-tune and adapt large language models (LLMs) and domain-specific models using techniques including LoRA, QLoRA, RLHF, and instruction tuning on client datasets
• Develop custom AI solution architectures tailored to specific client use cases — document intelligence, semantic search, automated reasoning, workflow automation, and more
• Integrate AI systems with client data infrastructure, APIs, vector databases (Pinecone, Weaviate, pgvector), and enterprise platforms
• Build robust evaluation and observability frameworks for AI systems — tracking performance, hallucination rates, latency, and output quality over time
• Lead technical discovery and solution design sessions with clients, translating ambiguous business problems into well-defined AI architectures
• Define and enforce best practices for prompt engineering, context management, memory architecture, and tool use within agentic systems
• Mentor junior AI engineers, reviewing designs and implementations with a focus on production readiness and maintainability
• Stay current on the rapidly evolving AI landscape and evaluate emerging tools, models, and techniques for applicability to client work

Requirements

• 3–5 years of experience in AI/ML engineering with a focus on applied, production systems
• Deep proficiency in Python and the modern AI/ML ecosystem (PyTorch, Hugging Face, LangChain, LlamaIndex, or equivalent)
• Hands-on experience building agentic AI systems — multi-agent orchestration, tool use, memory management, and autonomous workflow design
• Strong command of RAG architecture patterns including chunking strategies, embedding models, vector stores, and retrieval optimization
• Experience fine-tuning LLMs using parameter-efficient methods (LoRA, QLoRA) or full fine-tuning on custom datasets
• Familiarity with vector databases and semantic search infrastructure (Pinecone, Weaviate, Chroma, pgvector, or similar)
• Experience deploying AI systems to cloud environments (AWS, Azure, or GCP) with attention to scalability, cost, and latency
• Strong understanding of LLM evaluation methodologies (both automated and human-in-the-loop approaches)
• Demonstrated ability to lead client-facing technical engagements and independently own solution delivery end-to-end