2 days ago
Bengaluru, IndiaSenior
Responsibilities
- Partner with business and technical stakeholders to identify high-value AI use cases and translate ambiguous requirements into production-ready solutions.
- Design and build Generative AI, RAG, Advanced RAG, and Agentic AI applications, including retrieval pipelines and multi-agent workflows.
- Develop MCP servers and clients, tools, plugins, APIs, connectors, and secure integrations with enterprise systems and data sources.
- Build AI-enabled backend services and microservices using Python, FastAPI, Flask, REST APIs, asynchronous processing, and event-driven patterns.
- Create automated evaluation pipelines and LLMOps/GenAIOps capabilities for quality, monitoring, deployment, tracing, rollback, and production operations.
- Implement AI security guardrails, identity and access controls, privacy protections, and enterprise governance requirements.
- Rapidly prototype solutions and convert validated proofs of concept into secure, scalable, resilient, maintainable enterprise applications.
- Troubleshoot complex AI, retrieval, application, data, API, cloud, and integration issues through root-cause analysis.
- Produce technical designs, architecture diagrams, evaluation reports, runbooks, deployment documentation, and operational support procedures.
- Collaborate with Product Owners, Architects, Software Engineers, DevOps, Cybersecurity, Data Engineering, and business teams.
Requirements
- 8+ years of relevant software engineering, cloud engineering, AI/ML engineering, platform engineering, or solution engineering experience, including hands-on delivery of production-grade Generative AI, RAG, or Agentic AI systems.
- Strong Python programming experience with production-grade backend and AI application development.
- Hands-on experience building Generative AI and LLM applications using Azure OpenAI, OpenAI APIs, or equivalent enterprise model platforms.
- Strong experience with RAG, Advanced RAG, Agentic AI, tool and function calling, structured outputs, agent orchestration, and multi-agent workflows.
- Understanding of MCP hosts, clients, servers, tools, resources, prompts, authentication, authorization, and secure enterprise integration.
- Experience with prompt and context engineering, embeddings, semantic and vector search, hybrid retrieval, reranking, and retrieval-quality optimization.
- Experience with vector stores and search platforms such as Azure AI Search, PostgreSQL/pgvector, Redis, Pinecone, Qdrant, or Weaviate.
- Experience with document ingestion and knowledge pipelines, including document parsing, OCR, chunking, metadata extraction, indexing, and access-control-aware retrieval.
- Experience with Microsoft Semantic Kernel, LangChain, LangGraph, AutoGen, or equivalent AI orchestration technologies.
- Experience building APIs and microservices with FastAPI, Flask, REST, JSON, asynchronous programming, background workers, and message queues.
- Experience with Microsoft Azure and cloud-native application architecture.
- Experience with AI evaluation, LLMOps/GenAIOps, model and prompt versioning, experiment tracking, tracing, monitoring, telemetry, quality gates, and release management.
- Ability to optimize model selection, token usage, context size, latency, throughput, caching, reliability, and inference cost.
- Knowledge of Responsible AI, AI governance, privacy, PII handling, content safety, enterprise data protection, and OWASP Top 10 for LLM Applications risks.
- Experience with OAuth 2.0, OpenID Connect, SSO, JWT, RBAC, managed identities, Key Vault, and secrets management.
- Experience with Git, GitHub, pull requests, code review, automated testing, CI/CD, GitHub Actions, or Azure DevOps.
- Experience with Docker and containers; Kubernetes experience is preferred.
- Preferred experience includes Azure AI Foundry, Azure Machine Learning, Graph RAG, knowledge graphs, multimodal AI, model fine-tuning, MLflow, OpenTelemetry, LangSmith, PostgreSQL, Cosmos DB, Terraform, Bicep, Playwright, Pytest, and security testing.
- Strong hands-on engineering, debugging, system design, customer engagement, stakeholder communication, ownership, and production-readiness skills.
Benefits
- Regular full-time role with a 40-hour work week.
- Role locations are Hyderabad and Bangalore, India.
- AT&T provides equal employment opportunity and reasonable accommodations for qualified individuals with disabilities.
- AT&T is a fair chance employer and does not initiate a background check until an offer is made.
Tech Stack
Categories
Forward Deployed