AI Engineer (Python, FastAPI, LangGraph, LLM, RAG)

Position: AI Engineer

Skillset: Python, Fast API, Lang Graph, LLM,Orchestration,

RAG, PostgreSQL, Redis, Kubernetes, Open Telemetry

Experience: 4+yrs

Requirement: Full-Time

Location: Hyderabad (Work from Office)

Company Description: At NStarX, we live by our mission: being the Lodestar to Success for enterprises navigating the rapidly evolving digital landscape. We build cutting-edge, production-ready platforms that integrate advanced AI, cloud-native architecture, and robust data engineering to solve complex business challenges at scale. If you thrive in a collaborative environment that values technical excellence, architectural ownership, and production-first innovation, NStarX is where your impact will shine.

Job Description: We are seeking an experienced and driven Agentic AI Platform Engineer to design and build the core backend infrastructure for our enterprise-grade Agentic AI platform. In this role, you will move beyond prototyping to architect robust services handling agent orchestration, model routing, enterprise security, cost telemetry, and deep data integration. You will be instrumental in ensuring our AI systems are scalable, observable, secure, and seamlessly connected to enterprise data ecosystems.

Key Responsibilities:

• Core Infrastructure Development: Build and maintain critical backend services for model routing, dynamic agent orchestration, and multi-agent graph protocols.
• Integration & Data Pipelines: Implement and optimize production-grade RAG pipelines (retrieval, embedding/vector search, and grounding) and develop robust enterprise connectors (SQL, Kafka, Salesforce, SharePoint).
• Security & Compliance: Engineer built-in data protection mechanisms, including PII detection/redaction, RBAC/ABAC policy enforcement, and tamper-evident audit logs.
• FinOps & Observability: Instrument complete system telemetry (tracing, metrics, and logs) and design usage/cost tracking mechanisms for multi-provider AI workloads.
• Deployment & Scaling: Design resilient REST APIs and deploy production services onto cloud-managed container orchestrators (Kubernetes/ECS).

Skills and Experience:

Minimum Requirements:

• Expert Python & Async Frameworks: Extensive hands-on experience building production services using Fast API or equivalent asynchronous Python frameworks.
• Production AI Systems: Track record of shipping at least one LLM-powered system to production (multi-step orchestration, advanced RAG, or autonomous agents)prototypes or toy apps do not qualify.
• Agent/Graph Frameworks: Practical experience with agent frameworksLang Graph is highly preferred (Lang Chain, AutoGen, or comparable frameworks considered).
• Data & Caching: Strong competency running PostgreSQL and Redis in high-throughput production environments.
• Cloud & DevOps: Direct experience deploying and managing production services on Kubernetes (EKS) or AWS ECS.
• Observability: Solid fundamentals in system instrumentation, specifically using Open Telemetry tracing, structured logging, and metrics collection.
• API Design: Proven ability to design secure, clean, and scalable REST APIs integrated with legacy enterprise ecosystems.

Good to Have:

• LLM Gateway Management: Experience using LiteLLM, Kong, Portkey, or Azure APIM for virtual keys, budget tracking, fallback chains, and caching.
• Advanced Protocols: Exposure to Model Context Protocol (MCP) for building or consuming MCP servers/clients, as well as multi-agent protocols.
• Cloud AI Platforms: Hands-on experience with Amazon Bedrock, SageMaker, or cross-provider model routing.
• Compliance Engineering: Knowledge of WORM retention, hash chained audit logs, and automatic PII masking.
• AI FinOps: Experience setting up cost instrumentation and cost tracking dashboards for massive LLM workloads.
• Enterprise Middleware: Experience building enterprise data connectors or working with event streaming via Apache Kafka.
• Policy-as-Code: Familiarity with OPA-based policy enforcement and sophisticated RBAC/ABAC security design.