• Design, build, and scale backend services and APIs using Python with FastAPI, Django, and Flask
• Build and ship agentic AI systems: multi-step agents, tool calling, MCP integrations, and orchestration with frameworks like LangChain/LangGraph, LlamaIndex, CrewAI, or the Claude Agent SDK
• Develop RAG pipelines, including document ingestion, chunking, embeddings, vector databases, retrieval tuning, and evaluation
• Integrate and optimize LLMs (OpenAI, Anthropic Claude, Gemini, open-source models) for accuracy, latency, and cost
• Build data pipelines, analytics, and ML workflows using Pandas, NumPy, scikit-learn, and PyTorch or TensorFlow
• Set up LLM evaluation, guardrails, monitoring, and observability (LangSmith, Langfuse, or similar) for production AI systems
• Deploy and operate services on AWS, GCP, or Azure with Docker, Kubernetes, and CI/CD pipelines
• Lead technical design, break down work, mentor engineers, and set code-quality and AI-engineering standards
• Present AI solutions, demos, and technical roadmaps to clients, stakeholders, and leadership
• Take part in on-call rotations and production incident response

Requirements

• 3 to 6 years of professional software engineering experience, mostly in Python
• Strong production experience with FastAPI plus Django and/or Flask, including async programming and REST API design
• Hands-on experience building LLM-powered applications, including at least one RAG or agent-based system in production
• Working knowledge of vector databases (Pinecone, Weaviate, Qdrant, pgvector) and embedding models
• Solid data science fundamentals: data wrangling, statistics, model evaluation, and working with structured and unstructured data
• Strong SQL skills (PostgreSQL) and experience with NoSQL stores and Redis
• Hands-on cloud experience (AWS, GCP, or Azure) and containerization with Docker
• Strong testing habits (pytest) and clean, typed Python (type hints, Pydantic)
• Understanding of API security, OAuth 2.0, JWT, and responsible handling of sensitive data
• Excellent communication skills, with the ability to explain complex AI concepts simply, run client demos, and confidently represent and sell our technical approach
• Proven ability to lead projects and guide team members from proof of concept to production
• Curiosity and the ability to evaluate and adopt new AI tools and models quickly
  
  Nice to have
• Experience with fine-tuning, prompt optimization, or model distillation
• MLOps tools (MLflow, Kubeflow, SageMaker, Vertex AI, Bedrock)
• Experience building MCP servers or multi-agent systems
• Big data or streaming tools (Spark, Airflow, Kafka, dbt)
• Familiarity with Node.js or TypeScript for full-stack collaboration
• Published projects, research, Kaggle work, or open-source contributions in AI/ML
• AWS, GCP, or Azure AI or ML certifications