Senior Software Engineer - Python

We are seeking a skilled Software Engineer with strong expertise in Python to design, develop, and scale backend services and AI-powered applications. The ideal candidate will have hands-on experience building and deploying large language model (LLM) systems, including agentic AI and retrieval-augmented generation (RAG) pipelines. You will work with cutting-edge frameworks and cloud platforms to deliver robust, production-ready AI solutions, while also mentoring team members and collaborating closely with stakeholders.

Key Responsibilities

- Design, build, and scale backend services and APIs using Python frameworks such as FastAPI, Django, and Flask.
- Develop and deploy agentic AI systems involving multi-step agents, tool integrations, and orchestration using frameworks like LangChain, LangGraph, LlamaIndex, CrewAI, or Claude Agent SDK.
- Implement RAG pipelines including document ingestion, chunking, embeddings, vector database integration, retrieval tuning, and evaluation.
- Integrate and optimize LLMs from providers such as OpenAI, Anthropic Claude, Gemini, and open-source models, focusing on accuracy, latency, and cost-efficiency.
- Build data pipelines, analytics, and machine learning workflows using tools like Pandas, NumPy, scikit-learn, PyTorch, or TensorFlow.
- Establish LLM evaluation, guardrails, monitoring, and observability for production AI systems using platforms such as LangSmith or Langfuse.
- Deploy and operate services on cloud platforms (AWS, GCP, or Azure) using Docker, Kubernetes, and CI/CD pipelines.
- Lead technical design efforts, break down complex tasks, mentor engineers, and enforce code quality and AI engineering standards.
- Present AI solutions, demos, and technical roadmaps to clients, stakeholders, and leadership teams.
- Participate in on-call rotations and respond to production incidents to ensure system reliability.

Required Qualifications

- 3 to 6 years of professional software engineering experience, primarily using Python.
- Strong production experience with FastAPI and either Django or Flask, including asynchronous programming and REST API design.
- Proven experience building LLM-powered applications, with at least one RAG or agent-based system deployed in production.
- Working knowledge of vector databases such as Pinecone, Weaviate, Qdrant, or pgvector, and familiarity with embedding models.
- Solid foundation in data science concepts including data wrangling, statistics, model evaluation, and handling both structured and unstructured data.
- Proficiency in SQL (PostgreSQL) and experience with NoSQL databases and Redis.
- Hands-on experience with cloud platforms (AWS, GCP, or Azure) and containerization technologies like Docker.
- Strong testing practices using pytest and writing clean, typed Python code with type hints and Pydantic.
- Understanding of API security protocols including OAuth 2.0, JWT, and responsible management of sensitive data.
- Excellent communication skills with the ability to simplify complex AI concepts, conduct client demos, and effectively represent technical approaches.
- Demonstrated leadership in managing projects and guiding teams from proof of concept through to production deployment.
- Curiosity and adaptability to quickly evaluate and adopt new AI tools and models.

Preferred Qualifications and Benefits

- Experience with fine-tuning models, prompt optimization, or model distillation techniques.
- Familiarity with MLOps tools such as MLflow, Kubeflow, SageMaker, Vertex AI, or Bedrock.
- Experience building multi-agent systems or MCP servers.
- Knowledge of big data or streaming technologies like Spark, Airflow, Kafka, or dbt.
- Exposure to Node.js or TypeScript for full-stack collaboration.
- Contributions to published projects, research, Kaggle competitions, or open-source AI/ML initiatives.
- Certifications related to AI or ML on AWS, GCP, or Azure.

This role offers the opportunity to work at the forefront of AI engineering, contributing to innovative solutions that leverage the latest advancements in language models and cloud infrastructure. If you are passionate about building scalable AI systems and enjoy leading technical initiatives, we encourage you to apply.