AI Applications Engineer

We are seeking an AI Applications Engineer with deep expertise in AI systems development to join our engineering team. In this role, you’ll bridge the gap between ML research and real-world software delivery — designing, developing, and deploying intelligent applications powered by modern AI technologies including LLMs, multimodal models, and agentic workflows. You'll work closely with data scientists, ML engineers, and product managers to ship cutting-edge, scalable AI-powered features across web, backend, and mobile platforms.

DUTIES & RESPONSIBILITIES

• Design and build AI-native applications leveraging LLMs (e.g., OpenAI, Anthropic, Mistral) and multimodal models.
• Architect and implement agent-based workflows using frameworks like LangGraph, CrewAI, and AutoGen.
• Develop production-grade Python services using FastAPI or similar frameworks to expose AI functionalities via APIs.
• Fine-tune and serve custom LLMs for text, voice, and multimodal inputs; implement Retrieval-Augmented Generation (RAG) pipelines.
• Integrate vector search systems (e.g., Weaviate, Qdrant, Pinecone) for semantic memory and contextual reasoning.
• Use modern orchestration tools like LangChain, Flowise, Haystack, or n8n to prototype and scale intelligent flows.
• Leverage the OpenAI Function Calling / Tools API and Model Context Protocol (MCP) to build structured, dynamic LLM interactions.
• Implement continuous evaluation loops using synthetic data, human feedback (RLHF), and evaluation frameworks like Ragas or DeepEval.
• Collaborate with ML/infra teams to containerize, deploy, and monitor models using tools like Docker, MLflow, BentoML, or Kubernetes.
• Build scalable, secure, and efficient AI feature delivery pipelines across web and mobile platforms.
• Stay current with developments in foundation models, agent frameworks, multimodal AI, and open-source toolkits.

KNOWLEDGE & EXPERIENCE

Education:

• Bachelor's or Master’s degree in Computer Science, Software Engineering, Artificial Intelligence, or related discipline.

Experience:

• 2–4 years of experience building and deploying AI/ML-powered software.
• Proven track record of delivering LLM-integrated applications and/or agentic workflows in production.
• Experience in any of the following domains is a plus: NLP, computer vision, multimodal models, or conversational AI.

Knowledge and Skills:

• Proficient in Python and building production-grade RESTful APIs (FastAPI preferred).
• Experience working with foundation model APIs (OpenAI, Claude, Gemini, Mistral, Cohere).
• Familiarity with LangChain, LangGraph, CrewAI, Flowise, or similar frameworks.
• Experience implementing RAG pipelines and retrieval layers with vector databases (Pinecone, Qdrant, Weaviate, FAISS).
• Understanding of prompt engineering, structured memory (MCP), tool calling, and multi-turn conversation flows.
• Comfortable with tools like MLflow, Weights & Biases, or BentoML for model versioning and tracking.
• Ability to integrate with third-party services, RESTful APIs, and webhooks (Zapier, n8n, etc.).
• Familiarity with MLOps and CI/CD workflows for AI applications.
• Experience working with containerized environments (Docker, Kubernetes).
• Git, agile software development practices, and collaborative code workflows.
• Experience with speech recognition (Whisper), text-to-speech (ElevenLabs), or multimodal APIs (e.g., GPT-4o).