Senior Python Developer

Job Overview

We are seeking a highly skilled and visionary Senior Python Developer / AI Technical Lead with 6 to 8 years of experience to spearhead the design, development, and deployment of our next-generation AI-powered applications.

In this role, you will bridge the gap between robust backend engineering and cutting-edge Artificial Intelligence. You will be responsible for architecting high-performance APIs, implementing complex Retrieval-Augmented Generation (RAG) pipelines, and building autonomous Agentic AI systems. As a technical lead, you will also mentor junior developers, drive best practices, and collaborate closely with product and data science teams to turn AI innovations into production-ready enterprise solutions.

Key Responsibilities

• Backend & API Architecture: Design, build, and maintain scalable, high-performance, and secure APIs and microservices using Python and FastAPI.
• AI/LLM Integration: Integrate and orchestrate state-of-the-art Large Language Models (LLMs) from commercial providers (e.g., OpenAI, Anthropic) and open-source ecosystems (e.g., Llama, Mistral).
• Agentic AI Development: Architect and implement autonomous Agentic AI workflows, multi-agent systems, and tool-use capabilities using frameworks like LangGraph, CrewAI, or AutoGen.
• Advanced RAG Pipelines: Design, optimize, and maintain production-grade Retrieval-Augmented Generation (RAG) systems, ensuring accurate context retrieval, data ingestion chunking strategies, and minimized hallucination rates.
• Database & Vector Management: Optimize data persistence strategies using structured SQL databases (e.g., PostgreSQL), NoSQL databases (e.g., MongoDB), and specialized Vector Databases (e.g., Pinecone, Milvus, Qdrant, PGVector).
• Prompt Engineering & Optimization: Apply advanced Prompt Engineering techniques (e.g., Chain-of-Thought, ReAct, Few-Shot) and utilize programmatic evaluation frameworks to ensure LLM outputs are deterministic, safe, and aligned with business logic.
• Technical Leadership: Lead architectural reviews, enforce clean code principles (SOLID, DRY), establish CI/CD pipelines, and mentor a team of engineers in AI engineering best practices.

Required Technical Skills

• Core Programming: 6+ years of professional software development experience with expert-level proficiency in Python, asynchronous programming (asyncio), and profiling/optimization.
• Frameworks: Deep hands-on experience building production-ready RESTful and GraphQL APIs using FastAPI (or robust knowledge of Starlette/Pydantic).
• Generative AI & LLMs: Proven track record of working with LLM APIs, fine-tuning methodologies (preferred), and orchestration layers such as LangChain or LlamaIndex.
• Agentic Frameworks: Practical experience building AI Agents that can plan, use tools, and maintain state (e.g., LangGraph, CrewAI).
• Vector & Traditional Databases: Proficient in semantic search, embedding generation, and working with Vector DBs alongside traditional relational databases (PostgreSQL, MySQL) and caching layers (Redis).
• Prompt Engineering: Mastery in structured prompting, JSON-mode formatting, and evaluating prompt performance using tooling like LangSmith, Phoenix, or TruLens.
• DevOps & Cloud: Strong understanding of Docker, Kubernetes, and cloud infrastructure (AWS/GCP/Azure) to deploy and scale AI workloads.

Leadership & Soft Skills

• Problem-Solving: Exceptional analytical skills with a knack for debugging complex asynchronous systems and non-deterministic AI outputs.
• Mentorship: Proven experience guiding engineering teams, conducting constructive code reviews, and fostering an environment of continuous learning.
• Communication: Ability to translate complex technical AI concepts into clear business objectives for non-technical stakeholders.
• Agile Mindset: Experienced in working within Agile/Scrum frameworks, managing sprint deliverables, and adapting rapidly to evolving AI technologies.

Education & Qualifications

• Bachelors or Master’s degree in Computer Science, Software Engineering, Data Science, or a related technical field (or equivalent practical experience).
• 6–7 years of total professional software engineering experience, with at least 2+ years dedicated to building and deploying LLM/Generative AI applications in production.