Role Overview:This role involves designing, developing, and maintaining enterprise knowledge-base infrastructure and AI-enabled backend services. The focus is on building and optimizing Generative AI applications, RAG pipelines, and agent workflows using Python, FastAPI, and cloud-native technologies.
Key Responsibilities:- Design, develop, maintain and evolve enterprise knowledge-base infrastructure and AI-enabled backend services using Python and FastAPI.
- Build and optimize ingestion, chunking, embedding, vector indexing, semantic retrieval, reranking, context construction and grounded RAG pipelines.
- Develop LangChain and/or LangGraph-based agent workflows and reusable agent-runtime capabilities including tool calling, state management, retries, validation, guardrails and human approval where required.
- Integrate LLMs and enterprise knowledge sources securely through reusable APIs and services; use MCP or similar agent-tool integration patterns where appropriate.
- Implement PostgreSQL/vector database persistence, metadata filtering and retrieval patterns optimized for accuracy, latency and scale.
- Containerize services with Docker and deploy/manage them on Kubernetes.
- Build and maintain CI/CD pipelines using GitHub Actions, Jenkins or equivalent tools, including automated testing and deployment controls.
- Implement logging, tracing, metrics, dashboards and alerts using OpenTelemetry, Prometheus, Grafana and/or enterprise monitoring tools.
- Diagnose and resolve issues across APIs, retrieval pipelines, agent execution, databases, containers and distributed infrastructure.
- Improve performance, reliability, security, scalability and cost efficiency of production AI services.
- Establish automated tests and evaluation approaches for APIs, retrieval quality, grounded responses and agent behavior.
- Apply secure coding, access controls, audit logging, prompt/output validation and responsible-AI practices.
- Partner with product, architecture, data, security, DevOps and application teams to translate business needs into reusable knowledge and AI platform capabilities.
- Document architecture decisions, API contracts, operational procedures and knowledge-platform standards.
- Participate in Agile delivery, code reviews, technical design discussions, mentoring and production support.
Required Skills:- Strong hands-on experience with Python 3.11+ and production backend development.
- Strong experience building secure, scalable REST APIs and microservices using FastAPI; familiarity with Flask/Django is useful.
- Strong understanding of asynchronous Python, API design, validation, error handling, authentication/authorization, and enterprise integration patterns.
- Hands-on production experience building enterprise Generative AI applications using LLMs, RAG, semantic search, embeddings, and vector databases; ideally 2+ years of recent GenAI/RAG experience.
- Strong hands-on experience with LangChain and/or LangGraph for agentic workflows, orchestration, tool calling, multi-step execution, and controlled agent runtimes.
- Experience designing knowledge ingestion, document chunking, embedding generation, metadata enrichment, retrieval/reranking, context assembly, grounded generation, and response validation pipelines.
- Experience with PostgreSQL and vector search.
- Strong understanding of prompt engineering, AI agents, guardrails, human-in-the-loop patterns, AI evaluation, responsible AI, and secure enterprise data access.
- Strong hands-on experience with Docker and Kubernetes for production AI services.
- Experience with Git and CI/CD pipelines using GitHub Actions, Jenkins, or equivalent tools for automated build, test, and deployment.
- Experience with production monitoring and observability using OpenTelemetry, Prometheus, Grafana, Splunk/ELK, or equivalent tools.
- Ability to troubleshoot performance, reliability, retrieval quality, API, infrastructure, and production issues across distributed AI systems.
- Strong analytical, problem-solving, documentation, and cross-functional communication skills.
Qualifications:- 5-6 years of relevant experience.
Preferred Skills:- LangGraph for stateful agent orchestration and reusable agent-runtime patterns.
- PostgreSQL pgvector or equivalent production vector-database experience.
- Model Context Protocol (MCP), tool integration protocols, or reusable agent-tool interfaces.
- OpenTelemetry and production AI/agent observability; GitHub Actions experience.
- Experience with automated RAG/agent evaluation, regression datasets, retrieval-quality metrics, and grounded-response validation.
