We’re looking for an innovative ML Engineer to join our AI team and help design, prototype, and operationalize
advanced AI systems, including Retrieval-Augmented Generation (RAG) pipelines, MCP services, and agentic
workflows. You’ll work closely with Python Developers and MLOps Engineers to bring AI-powered features
from concept to production.

Responsibilities:

● Design, prototype, and iterate on AI models, RAG pipelines, MCP services, and agentic reasoning
systems.
● Develop AI-powered services using frameworks such as LangChain, LangGraph, CrewAI, LlamaIndex,
Haystack, and DSPy.
● Build and optimize prompts for AI-driven tasks like chat, summarization, information extraction, and
decision support.
● Integrate and tune vector databases (e.g., Chroma, FAISS, Pinecone, Qdrant) to optimize vector
search workflows.
● Collaborate with Python Developers to define service interfaces, APIs, and operational
requirements.
● Implement task decomposition, memory management, and tool-use strategies within agentic
systems.
● Monitor AI system performance, operational risks, and prompt evaluation metrics.
● Stay current with emerging AI frameworks, architectures, and best practices in AI observability and
evaluation.

Requirements:

●Strong Python development skills with an emphasis on clean, scalable, and modular code.
● Hands-on experience working with LLMs and agent frameworks.
● Solid understanding of RAG architecture, vector search concepts (cosine similarity, MMR, late
interaction), and system design.
● Experience building multi-step agentic workflows and reasoning systems.
● Familiarity with AI performance metrics, model drift detection, and operational monitoring.
● Awareness of AI limitations, including latency, hallucination risks, and explainability challenges.
● Experience with DSPy or other prompt optimization tools is a plus.
● A curious, experimental mindset with a passion for testing emerging AI tools and frameworks.

● Bachelor’s degree in Computer Science or equivalent - preferred.