About the role
We are looking for a Senior Backend Engineer with 5–7 years of backend engineering experience in Python, including at least 2 years of hands-on work with generative AI, LLM-based agent development, and API-driven integrations.
This is a hands-on engineering role. You will build scalable backend systems, microservices, production-ready AI agents, and end-to-end GenAI applications. GenAI expertise is essential, but a significant part of the role is core engineering: distributed systems, deployment automation, observability, and production readiness.
You will collaborate closely with Product, Infrastructure, and Design, contributing across the full development lifecycle, from architecture and coding to testing, debugging, deployment, and long-term support.
What you will do
Agent & application development
- Design, build, and maintain LLM-powered agents using LangChain, LangGraph, FastAPI, Pydantic, and related Python ecosystem tools.
- Implement orchestration, agent memory, tool calling, and multi-agent workflows.
- Build reusable internal Python packages and libraries, and maintain clean, modular codebases.
GenAI integration & LLM engineering
- Work with RAG pipelines, embeddings, vector search, and LLM inference APIs (OpenAI, Azure OpenAI, Anthropic, Mistral, Ollama, and others).
- Integrate and optimize vector stores such as Pinecone, Weaviate, Qdrant, and FAISS.
- Implement prompt engineering, evaluation frameworks, model routing, and model performance monitoring.
On-prem & enterprise LLM hosting
- Contribute to the deployment, fine-tuning, optimization, and monitoring of self-hosted and enterprise LLMs.
- Support inference optimization, GPU utilization, model quantization, and serving pipelines.
Backend & microservices engineering
- Build robust RESTful and event-driven microservices with strong observability, tracing, latency optimization, and failover strategies.
- Work with SQLAlchemy, relational databases, and optimized data models.
Deployment, DevOps & production readiness
- Write efficient Dockerfiles, manage Kubernetes deployments, and contribute to CI/CD pipelines.
- Implement logging, tracing, debugging, and automated testing strategies.
- Support live environments with high availability and rapid troubleshooting.
What you bring
- Strong Python expertise with a track record of building production-grade applications.
- Experience with FastAPI, Pydantic, SQLAlchemy, and asynchronous programming.
- Proven ability to design and develop REST APIs and distributed microservices.
- Practical experience with RAG, embeddings, vector databases, and LLM frameworks.
- Hands-on experience with Docker, Kubernetes, CI/CD, and cloud platforms (AWS or Azure).
- Ability to troubleshoot and debug complex backend and GenAI systems in production.
- Experience with multi-agent systems, tool integrations, and emerging standards such as the Model Context Protocol (MCP).
Nice to have
- Experience building and publishing Python packages, internal SDKs, or tooling libraries.
- Contributions to open-source projects, particularly in Python, AI/ML, or DevOps.
- Exposure to multimodal GenAI (text, image, audio).
- Strong fundamentals in algorithms, distributed systems, and system design.
- Experience with model fine-tuning, dataset preparation, and prompt evaluation frameworks.
- Experience deploying GPU workloads with NVIDIA Triton, vLLM, Ray Serve, or equivalent.
- Familiarity with cost optimization strategies for AI workloads.