About the Role

What You'll Do

• LLM & Agent Development: Design and develop LLM-powered applications, chatbots, and AI agents using Python, LangChain, and LangGraph — our required agent framework.
• RAG Pipelines: Build Retrieval-Augmented Generation solutions — document processing, chunking, embedding generation, retrieval, and vector search — to improve response accuracy and relevance.
• Prompt Engineering: Write, test, and iterate on prompts and context templates for specific use cases; assist with basic fine-tuning or parameter-efficient tuning (LoRA/PEFT) as needed.
• Agentic Systems: Build AI agents, tool/function calling, and multi-step or agent-to-agent workflows (e.g., MCP) so agents can call internal/external APIs under senior engineers' architectural direction.
• Backend & APIs: Develop backend services and REST APIs using FastAPI, and build the data pipelines that connect GenAI features end-to-end, from ingestion to the user-facing interface.
• Cloud & MLOps: Deploy and operate AI workloads on Microsoft Azure, using managed services such as Azure OpenAI Service and Azure AI Search, plus basic containerization (Docker).
• Evaluation & Monitoring: Implement logging, monitoring, evaluation, and optimization for LLM applications (accuracy, relevance, latency, cost); flag and help investigate issues like hallucinations.
• Automation & Orchestration: Build simple automation workflows (e.g., n8n, Zapier, Make, or Python scripts) to reduce manual effort in day-to-day AI operations.
• Cross-Functional Collaboration: Work with product managers, software engineers, and data scientists to translate business requirements into scalable, well-scoped AI solutions.
• Security, Privacy & Responsible AI: Follow established data privacy, security, and responsible-AI guidelines; help identify risks like prompt injection or data leakage in the features you build.

Required Skills & Qualifications

• Education: Bachelor's degree in Computer Science, AI/ML, Data Science, or a related field (or equivalent practical experience).
• Experience: 2–3 years of professional software engineering experience, including at least 6–12 months of hands-on exposure to LLMs or Generative AI.
• Python (Mandatory): Strong, hands-on proficiency in Python — mandatory for all GenAI development on this team.
• LangChain & LangGraph (Mandatory): Hands-on experience building LLM applications and agent workflows with LangChain and LangGraph — a non-negotiable requirement for this role.
• Azure (Mandatory): Hands-on experience with Microsoft Azure; familiarity with Azure OpenAI Service and/or Azure AI Search is required. (Azure is our platform of choice — experience with AWS or GCP alone does not meet this requirement.)
• APIs: Experience developing REST APIs using FastAPI or a similar framework.
• Vector Search: Practical understanding of RAG, embeddings, vector databases, and semantic search (e.g., Azure AI Search, Pinecone, Qdrant, Weaviate, pgvector).
• Data: Working knowledge of SQL and relational databases.
• Engineering Fundamentals: Solid fundamentals — Git/version control, basic testing and debugging practices, clean code, and willingness to learn CI/CD.
• Growth Mindset: Curiosity and eagerness to learn — comfortable experimenting, asking questions, and iterating quickly with feedback from senior engineers.

Good to Have

• Personal projects, hackathon entries, or coursework involving LLMs, chatbots, or Generative AI (a portfolio or GitHub link is a plus).
• Experience with Azure AI Foundry, or LLM evaluation/observability tools such as Lang Smith.
• Experience with MCP (Model Context Protocol) or structured/tool-calling outputs.
• Exposure to multimodal AI, OCR, or document-intelligence pipelines (agentic RAG).
• Familiarity with Docker and containerization concepts, and CI/CD via Azure DevOps or GitHub Actions.
• Relevant certifications (e.g., Microsoft Certified: Azure AI Engineer Associate, Azure AI Fundamentals, or DeepLearning.AI GenAI courses).