Senior AI Engineer — 6+ Years | Generative AI, RAG & AgentsWe're hiring a Senior AI Engineer to design, build, deploy, and scale enterprise-grade Generative AI systems — copilots, chatbots, knowledge assistants, RAG platforms, and autonomous agentic workflows.

This is a hands-on senior IC role. You'll own solutions end to end: concept → architecture → implementation → evaluation → deployment → production operations → continuous optimization, working alongside AI Architects, Consultants, Product Managers, and engineering teams.

What you'll do

- Build and maintain enterprise AI applications: copilots, chatbots, knowledge assistants, and agentic workflows
- Turn solution architecture and ambiguous business requirements into robust, maintainable, production-ready systems
- Architect scalable RAG pipelines over enterprise data — ingestion, parsing, chunking, metadata enrichment, embeddings, indexing, hybrid and semantic search, reranking, context construction
- Design AI agent systems with tool calling, state management, planning, memory, workflow orchestration, human-in-the-loop controls, guardrails, and failure recovery
- Develop backend services, APIs, and orchestration layers in Python and FastAPI; build production UIs in React and Next.js
- Integrate LLMs, embedding models, enterprise applications, databases, external APIs, and identity platforms into cohesive solutions
- Establish LLM evaluation covering quality, relevance, groundedness, hallucination, latency, reliability, and cost
- Optimize for performance, latency, scalability, token consumption, model utilization, and operational cost
- Implement automated testing across unit, integration, API, workflow, retrieval, and AI evaluation layers
- Own CI/CD, infrastructure automation, release and rollback; deploy across cloud, containerized, and Kubernetes environments
- Implement production observability — monitoring, logging, distributed tracing, alerting, and operational controls
- Apply AI security and governance: authN/authZ, data protection, prompt injection defense, sensitive-data handling, model access, and auditability
- Lead design reviews and code reviews,



mentor mid-level and junior engineers, and build reusable AI frameworks, components, accelerators, and standards
- Evaluate emerging models, agent frameworks, retrieval tech, and cloud AI services, and drive continuous improvement from production telemetry, evaluations, and user feedback

What you need

- 6+ years in qualified software engineering, AI engineering, or related technology work
- Strong production Python for backend, AI, and automation
- Proven delivery of production Generative AI applications — not POCs
- Hands-on with LLMs, RAG, embeddings, prompt engineering, AI agents, tool calling, and agentic workflows
- LangChain, LangGraph, or equivalent orchestration frameworks; stateful, multi-step workflows with guardrails, validation, error handling, and human-in-the-loop controls
- Deep understanding of end-to-end RAG architecture
- Production React and/or Next.js
- REST APIs, FastAPI, microservices, authentication/authorization, and distributed application architecture
- Vector databases and semantic/hybrid search
- Relational databases, data modeling, caching, async processing, and event-driven architecture
- Git-based workflows, branching strategies, code review, automated testing, and CI/CD
- Cloud-native development, containerization, deployment, and operations
- Proven ability to troubleshoot complex production issues and optimize performance and reliability
- Strong fundamentals: design patterns, clean architecture, SOLID, maintainable code

Nice to have

- Azure OpenAI, Azure AI Services, Microsoft Copilot Studio, AWS Bedrock, or Google Vertex AI
- Azure AI Search, Pinecone, Weaviate, Chroma, pgvector, or equivalent
- LangGraph, Semantic Kernel, AutoGen, CrewAI, or similar agent frameworks
- Docker, Kubernetes, Helm,



and cloud-native deployments; Terraform or equivalent IaC
- LLMOps / GenAIOps, AI evaluation frameworks, and observability platforms
- Prompt injection defense, AI security, responsible AI, data and model governance
- Distributed systems, queues, async processing, and scalable service design
- OAuth2, OpenID Connect, Azure AD / Entra ID, RBAC, managed identities
- Designing reusable AI platforms, internal frameworks, or engineering accelerators
- Leading technical initiatives or mentoring engineering teams

What "senior" means here You own AI features from architecture to production. You spot architectural risk before implementation, choose models, frameworks, databases, and infrastructure against real constraints, and make explicit trade-offs between quality, latency, scalability, security, and cost. You design for the reality that LLMs produce unexpected outputs — retries, fallbacks, timeouts, degraded modes, human escalation — and you rely on evaluation and observability rather than manual testing.

You review and improve architects' designs, lead complex multi-service implementations, mentor other engineers, and debug production with logs, traces, metrics, and evals.

Success isn't measured by AI features shipped. It's measured by AI systems that run in production and create measurable business value: secure, reliable, observable, scalable, cost-efficient, evaluated, maintainable.

Skills: Python · FastAPI · React · Next.js · LLMs · Generative AI · RAG · AI Agents · LangChain · LangGraph · Prompt Engineering · Tool Calling · LLM Evaluation · Guardrails · Embeddings · Semantic & Hybrid Search · Reranking · Vector Databases · Azure AI Search · Pinecone · Weaviate · Chroma · pgvector · PostgreSQL · Redis · REST APIs · Microservices · Event-Driven Architecture · Distributed Systems · OAuth2 / OIDC · Docker · Kubernetes · Helm · Terraform · CI/CD · GitHub Actions · Azure DevOps · Observability · Distributed Tracing · LLMOps / GenAIOps · Azure · AWS · GCP · Azure OpenAI · AWS Bedrock · Vertex AI · AI Security · Responsible AI

📌 Senior AI Engineer (Hyderabad)
🏢 CittaAI
📍 Hyderabad