Artificial Intelligence Engineer

Job Title: LLM Engineer / AI Engineer Position Overview We are seeking a highly technical LLM / AI Engineer to design, optimize, and deploy AI models powering next-generation Agentic AI initiatives . This role will be instrumental in ensuring AI agents not only generate responses but also execute tasks with precision, reliability, and business context awareness. The ideal candidate will have a strong builder mindset , capable of taking raw AI models and transforming them into scalable, production-ready systems that improve operational efficiency and significantly shorten support cycles.

Your focus will include model selection, prompt engineering, RAG optimization, tool-use logic, evaluation frameworks, and latency optimization to build enterprise-grade AI solutions. Key Responsibilities Model Engineering Design, implement, and optimize LLM pipelines using both proprietary models (OpenAI, Anthropic, etc.) and open-source models (Llama, Mistral, etc.) to achieve the best cost-performance balance. Fine-tune and optimize models for production use cases across enterprise workflows.

RAG Architecture Build, deploy, and maintain advanced Retrieval-Augmented Generation (RAG) systems. Enable AI agents with real-time access to internal documentation, structured/unstructured data, customer history, and platform intelligence. Improve retrieval accuracy, chunking strategies, embedding pipelines, and context relevance.

Prompt Engineering & Optimization Develop, test, and version-control complex prompt templates at scale. Apply advanced prompting techniques such as Few-Shot Prompting, Chain-of-Thought, Function Calling, and Agentic Workflows . Continuously improve reasoning quality and response reliability.

Evaluation & Testing Design automated AI evaluation frameworks including LLM-as-a-Judge , hallucination detection, toxicity scoring, and factual accuracy testing. Establish robust testing and validation pipelines before production deployment. Agent Tool-Use Logic Develop reliable and secure tool-use frameworks enabling AI agents to interact with: APIs Databases External services Custom business functions Ensure safe orchestration and fallback mechanisms.

Latency & Performance Optimization Optimize inference pipelines, retrieval systems, and orchestration layers for near real-time response performance. Improve scalability, throughput, and cost efficiency across AI workloads. Required Qualifications Technical Background Strong background in Backend Engineering, AI Engineering, Data Science, or NLP-focused Machine Learning .

Architecture & Systems Deep experience in designing scalable distributed systems and production-grade AI architectures. Programming Advanced proficiency in Python Experience with data libraries such as NumPy, Pandas AI / LLM Frameworks Hands-on experience with one or more: LangChain LlamaIndex Haystack Vector Search & Retrieval Experience with: Vector databases Semantic search systems such as: FAISS Chroma Pinecone Embeddings & Retrieval Optimization Deep understanding of embedding models and semantic retrieval optimization Ability to improve domain-specific contextual relevance LLMOps / AI in Production Experience with AI monitoring, model evaluation, observability, and performance drift management in production environments Preferred Qualifications Experience in high-throughput environments such as Trading, FinTech, or similar data-intensive industries Prior experience building and deploying autonomous / agentic AI systems in production Familiarity with Anthropic Claude ecosystem and modern agent orchestration frameworks Experience with API orchestration, tool calling, and enterprise AI governance Why Join Us? Opportunity to work on transformative AI initiatives with real business impact Build cutting-edge Agentic AI systems in a fast-paced and innovation-driven environment Work with advanced AI/ML technologies and modern engineering stacks Competitive compensation and strong growth opportunities Collaborate with high-performing global teams and domain experts Interested candidates can share their updated resume at: