Senior Software Engineer (AI)

Role Overview

Key Responsibilities

• Design and develop production-ready Generative AI and LLM-based applications.
• Build scalable Retrieval-Augmented Generation (RAG) pipelines using embeddings, vector databases, reranking, retrieval, and contextual generation.
• Develop Agentic AI workflows using frameworks such as LangGraph and LangChain.
• Implement multi-agent workflows involving planning, reasoning, tool calling, delegation, memory, and orchestration.
• Integrate LLMs from OpenAI, Anthropic, Google Gemini, and other providers.
• Develop backend services and AI APIs using Python, FastAPI, and REST APIs.
• Design and implement LLM evaluation frameworks to measure accuracy, relevance, groundedness, hallucination, latency, and other quality metrics.
• Implement AI guardrails, validation, safety controls, structured outputs, and responsible AI practices.
• Work with PostgreSQL, vector databases, and graph databases to build AI knowledge systems.
• Containerize and deploy AI applications using Docker and cloud platforms such as Azure/AWS.
• Optimize LLM applications for performance, scalability, reliability, and cost.
• Collaborate with architects, frontend/backend engineers, DevOps, and business stakeholders.
• Participate in technical design, code reviews, troubleshooting, and production support.
• Stay current with emerging developments in LLMs, Agentic AI, RAG, open-source models, and AI infrastructure.

Must-Have Skills

Programming & Backend

• Strong hands-on experience with Python
• FastAPI
• REST API development
• Backend application architecture and development

Generative AI & LLM

• LLM application development
• RAG architecture and implementation
• Prompt engineering
• Embeddings and semantic search
• Vector databases
• LLM integration and orchestration
• Experience with one or more of:
  • OpenAI
  • Anthropic
  • Google Gemini

Agentic AI

• Hands-on experience building AI Agents
• LangGraph and/or LangChain
• Tool/function calling
• Agent workflows and orchestration
• Multi-agent systems
• Agent state and memory management

Data & Infrastructure

• PostgreSQL
• Vector databases
• Docker
• Azure and/or AWS
• API integration and microservices

AI Quality & Security

• LLM evaluation
• RAG evaluation
• Hallucination detection/mitigation
• AI guardrails
• Structured output and schema validation
• Understanding of AI security and responsible AI practices

Preferred / Good-to-Have Skills

• Neo4j / GraphRAG
• Model Context Protocol (MCP)
• vLLM
• Ollama
• Open-source LLMs such as Llama, Qwen, Mistral, etc.
• LoRA / parameter-efficient fine-tuning
• Model fine-tuning
• Kubernetes
• CI/CD and Azure DevOps/GitHub Actions
• React / Next.js
• Redis or other caching technologies
• Experience with cloud-based AI/ML infrastructure
• Experience optimizing inference performance and LLM costs

What We Are Looking For

• Strong problem-solving and analytical skills.
• Ability to convert business requirements into practical AI solutions.
• Strong understanding of LLM architecture and modern GenAI patterns.
• Ability to write clean, maintainable, production-quality code.
• Comfortable working in a fast-moving AI engineering environment.
• Ability to independently investigate new AI technologies and implement POCs/prototypes.
• Good understanding of software engineering principles, APIs, databases, security, and deployment.
• Strong communication and collaboration skills.
• Ability to work closely with an AI Architect / Technical Lead while taking ownership of implementation.