Software Developer

Overview of Role

Seasoned Software Developer with deep expertise in Python-based backend development (framework-agnostic, without a hard dependency on Django) and cloud-native application delivery. Adept at building scalable platforms, designing RESTful APIs, and integrating modern AI/LLM capabilities into production systems. Experienced with technologies like FastAPI, React, and cloud platforms such as Azure and GCP. Known for driving solution delivery, mentoring teams, and aligning technology initiatives with business goals.

Responsibilities:

• Architect and deliver scalable backend solutions using modern Python frameworks

• Design, build, and integrate LLM-powered features (RAG pipelines, AI agents, tool/function calling) into production applications

• Design and maintain robust RESTful (and optionally GraphQL) APIs

• Build event-driven systems and manage distributed/background job processing

• Oversee cloud deployments and infrastructure on Azure and GCP

• Implement CI/CD, observability, and cost/performance optimization for AI workloads

• Lead cross-functional teams, mentor engineers, and uphold high engineering standard

Core Skills:-

1. Primary: Python (FastAPI, Flask), API Design, Cloud-Native Architecture, Async programming (asyncio) for building event-driven systems and handling distributed/background jobs

2. Database: SQL (PostgreSQL, MySQL), ORM (SQLAlchemy)

3. Secondary: React, JavaScript (ES6+), HTML5, CSS3

4. Cloud & DevOps: Azure, GCP, Docker, Kubernetes, CI/CD

5. Tools & Practices: SQLAlchemy, Agile, Git, Terraform, Pytest.

AI / LLM Engineering Skills:-

LLM APIs: OpenAI, Google Gemini, Anthropic Claude (incl. Azure OpenAI / Vertex AI)

• Prompt Engineering and AI Agents (tool use, function calling, multi-agent

orchestration)

• RAG (Retrieval-Augmented Generation) chunking, embeddings, retrieval strategies

• Vector Databases: e.g. Pinecone, Weaviate, Chroma, pgvector, FAISS, Milvus

• AI Frameworks: LangChain / LangGraph, Google ADK, LlamaIndex

• MCP (Model Context Protocol)

Good to Have:-

LLM Ops & evaluation: LangSmith / LangFuse, prompt versioning, eval frameworks

(RAGAS, DeepEval), guardrails/hallucination mitigation

• Embeddings & model tuning: text embedding models, fine-tuning / LoRA, structured

output (JSON mode, Pydantic-based parsing)

• Data & pipelines: Pandas, background jobs/queues (Celery, Redis), streaming

responses (SSE/WebSockets)

• API hardening: authentication/authorization (OAuth2, JWT), rate limiting, caching

• Message brokers / event-driven: Kafka, RabbitMQ, or Pub/Sub

• Security & governance: Data Privacy, Responsible-AI / Content Moderation

• Testing & quality: unit/integration testing, type checking (mypy), linting (ruff)